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

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

Neuron 4307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9907. Min Act: -0.0001

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1094338 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1060162 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9169. Min Act: -0.0001

Data Index: 1163164 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9361. Min Act: -0.0001

Data Index: 304658 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8713. Min Act: -0.0001

Data Index: 434321 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8408. Min Act: -0.0001

Data Index: 159974 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1107591 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1195487 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7753. Min Act: -0.0001

Data Index: 387716 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8205. Min Act: -0.0001

Data Index: 307417 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8037. Min Act: -0.0001

Data Index: 374756 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7314. Min Act: -0.0001

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7075. Min Act: -0.0001

Data Index: 907678 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7161. Min Act: -0.0001

Data Index: 31768 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7289. Min Act: -0.0001

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.6994. Min Act: -0.0001

Data Index: 662541 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.6593. Min Act: -0.0001

Data Index: 458738 (C4 (Web Text))

Max Activating Token Index: 863