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

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

Neuron 751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0000

Data Index: 300251 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0407. Min Act: -0.0001

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0402. Min Act: -0.0001

Data Index: 20647 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0394. Min Act: -0.0000

Data Index: 144027 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1079061 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0384. Min Act: -0.0000

Data Index: 325663 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0371. Min Act: -0.0000

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0330. Min Act: -0.0000

Data Index: 889778 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0328. Min Act: -0.0001

Data Index: 799364 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0334. Min Act: -0.0000

Data Index: 67688 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0328. Min Act: -0.0000

Data Index: 240411 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0316. Min Act: -0.0000

Data Index: 350480 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0308. Min Act: -0.0000

Data Index: 525149 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0301. Min Act: -0.0001

Data Index: 701092 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0268. Min Act: -0.0000

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0271. Min Act: -0.0001

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1585542 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0276. Min Act: -0.0000

Data Index: 713393 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0274. Min Act: -0.0000

Data Index: 818340 (C4 (Web Text))

Max Activating Token Index: 425