< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 12 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.5460. Min Act: -0.1700

Data Index: 7515938 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.5303. Min Act: -0.1700

Data Index: 4685268 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4833. Min Act: -0.1699

Data Index: 9798846 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4833. Min Act: -0.1700

Data Index: 102688 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4676. Min Act: -0.1700

Data Index: 4571660 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4676. Min Act: -0.1700

Data Index: 2401084 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4676. Min Act: -0.1699

Data Index: 2805140 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4676. Min Act: -0.1700

Data Index: 947049 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4363. Min Act: -0.1700

Data Index: 94595 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4363. Min Act: -0.1700

Data Index: 1324944 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4363. Min Act: -0.1700

Data Index: 120714 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4363. Min Act: -0.1700

Data Index: 8078633 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 3338047 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 8308184 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 9021879 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 2512937 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 4462589 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 6223009 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 3085600 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5460. Min Range: -3.5460

Max Act: 3.4206. Min Act: -0.1700

Data Index: 4956557 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #19