Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2671 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.6389. Min Act: -0.0000

Data Index: 535710 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1994875 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4901. Min Act: -0.0000

Data Index: 1176552 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5737. Min Act: -0.0000

Data Index: 671566 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.8532. Min Act: -0.0000

Data Index: 786822 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1801986 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1792125 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5006. Min Act: -0.0000

Data Index: 712223 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.7449. Min Act: -0.0000

Data Index: 134615 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4847. Min Act: -0.0000

Data Index: 610147 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1506803 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4193. Min Act: -0.0000

Data Index: 269439 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4472. Min Act: -0.0000

Data Index: 112377 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.3728. Min Act: -0.0000

Data Index: 400245 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1133013 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.3550. Min Act: -0.0000

Data Index: 1465083 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1710765 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4415. Min Act: -0.0000

Data Index: 1753437 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1605767 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.3197. Min Act: -0.0000

Data Index: 654011 (The Pile)

Max Activating Token Index: 275