< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6074. Min Act: -0.1700

Data Index: 1182087 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.7483. Min Act: -0.1699

Data Index: 5842545 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6700. Min Act: -0.1700

Data Index: 831667 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4978. Min Act: -0.1700

Data Index: 10629868 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5761. Min Act: -0.1700

Data Index: 5666241 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4194. Min Act: -0.1690

Data Index: 300390 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5761. Min Act: -0.1700

Data Index: 8463016 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4821. Min Act: -0.1700

Data Index: 1876321 (The Pile)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5448. Min Act: -0.1699

Data Index: 3157953 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3566. Min Act: -0.1700

Data Index: 6482225 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5761. Min Act: -0.1699

Data Index: 6049883 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4978. Min Act: -0.1700

Data Index: 6630276 (The Pile)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6700. Min Act: -0.1700

Data Index: 5445109 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5761. Min Act: -0.1700

Data Index: 9495562 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4978. Min Act: -0.1700

Data Index: 4141995 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6387. Min Act: -0.1700

Data Index: 4380130 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3253. Min Act: -0.1700

Data Index: 4438598 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5134. Min Act: -0.1700

Data Index: 1900061 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5604. Min Act: -0.1700

Data Index: 7347801 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3566. Min Act: -0.1700

Data Index: 7615598 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #19