Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0000

Data Index: 52088 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1642417 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0620. Min Act: -0.0000

Data Index: 551424 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0475. Min Act: -0.0000

Data Index: 324312 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0542. Min Act: -0.0000

Data Index: 228616 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1469511 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0473. Min Act: -0.0000

Data Index: 642604 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0460. Min Act: -0.0000

Data Index: 140690 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1386397 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1314395 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0534. Min Act: -0.0000

Data Index: 823102 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1622056 (Python Code)

Max Activating Token Index: 996

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0488. Min Act: -0.0000

Data Index: 77453 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1159775 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0414. Min Act: -0.0000

Data Index: 442941 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1160540 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0487. Min Act: -0.0000

Data Index: 609775 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0453. Min Act: -0.0000

Data Index: 559762 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1415830 (Python Code)

Max Activating Token Index: 316

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1442258 (Python Code)

Max Activating Token Index: 510