< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 75 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5105. Min Act: -0.0004

Data Index: 534333 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4977. Min Act: -0.0004

Data Index: 972944 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4574. Min Act: -0.0004

Data Index: 1825690 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4855. Min Act: -0.0004

Data Index: 1511932 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4349. Min Act: -0.0004

Data Index: 163149 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4754. Min Act: -0.0004

Data Index: 949951 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4436. Min Act: -0.0004

Data Index: 50925 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4554. Min Act: -0.0004

Data Index: 458387 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4501. Min Act: -0.0004

Data Index: 757617 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4476. Min Act: -0.0004

Data Index: 1539602 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4604. Min Act: -0.0004

Data Index: 103894 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4276. Min Act: -0.0004

Data Index: 1341582 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4511. Min Act: -0.0004

Data Index: 730754 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4357. Min Act: -0.0004

Data Index: 1774449 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4331. Min Act: -0.0004

Data Index: 1053853 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4284. Min Act: -0.0004

Data Index: 1043555 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4280. Min Act: -0.0004

Data Index: 284667 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4082. Min Act: -0.0004

Data Index: 1544639 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4207. Min Act: -0.0004

Data Index: 1666132 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4195. Min Act: -0.0004

Data Index: 704707 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #19