Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1869 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7188. Min Act: -0.0000

Data Index: 411229 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7296. Min Act: -0.0000

Data Index: 979865 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1809801 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7008. Min Act: -0.0000

Data Index: 506554 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6367. Min Act: -0.0000

Data Index: 241467 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6772. Min Act: -0.0000

Data Index: 155963 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6409. Min Act: -0.0000

Data Index: 478613 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1873613 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1988601 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6463. Min Act: -0.0000

Data Index: 864816 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1241504 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6410. Min Act: -0.0000

Data Index: 221839 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6135. Min Act: -0.0000

Data Index: 89406 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1222652 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6144. Min Act: -0.0000

Data Index: 18420 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1830678 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1269470 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6326. Min Act: -0.0000

Data Index: 265509 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6432. Min Act: -0.0000

Data Index: 123650 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1768628 (The Pile)

Max Activating Token Index: 827