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

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

Neuron 205 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0266. Min Range: -1.0266

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1116065 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9994. Min Act: -0.0000

Data Index: 944318 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8955. Min Act: -0.0000

Data Index: 834579 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8347. Min Act: -0.0000

Data Index: 17946 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8298. Min Act: -0.0000

Data Index: 234992 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7977. Min Act: -0.0000

Data Index: 631739 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7560. Min Act: -0.0000

Data Index: 393848 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1006391 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7027. Min Act: -0.0000

Data Index: 427607 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1315446 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1139508 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7396. Min Act: -0.0000

Data Index: 195509 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1106378 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6554. Min Act: -0.0000

Data Index: 868440 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.5800. Min Act: -0.0000

Data Index: 518321 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6630. Min Act: -0.0000

Data Index: 95481 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1022474 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1265482 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6576. Min Act: -0.0000

Data Index: 836504 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1270353 (C4 (Web Text))

Max Activating Token Index: 1016