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

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

Neuron 39 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.6205. Min Act: -0.0001

Data Index: 1051398 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3573. Min Act: -0.0001

Data Index: 1357059 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1405204 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.4125. Min Act: -0.0001

Data Index: 1582800 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3743. Min Act: -0.0001

Data Index: 1481760 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3054. Min Act: -0.0001

Data Index: 1653332 (Python Code)

Max Activating Token Index: 870

Text #6

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1644853 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3088. Min Act: -0.0001

Data Index: 1399754 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3438. Min Act: -0.0001

Data Index: 713274 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.4130. Min Act: -0.0001

Data Index: 1139236 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1449148 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2508. Min Act: -0.0001

Data Index: 1367869 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2504. Min Act: -0.0001

Data Index: 1485671 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2382. Min Act: -0.0001

Data Index: 540715 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1647361 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2352. Min Act: -0.0001

Data Index: 1561966 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2635. Min Act: -0.0001

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.3118. Min Act: -0.0001

Data Index: 1499231 (Python Code)

Max Activating Token Index: 627

Text #18

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2331. Min Act: -0.0000

Data Index: 988096 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 1.6205. Min Range: -1.6205

Max Act: 1.2249. Min Act: -0.0001

Data Index: 1190328 (C4 (Web Text))

Max Activating Token Index: 301