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

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

Neuron 4140 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.7244. Min Act: -0.0000

Data Index: 983601 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.7233. Min Act: -0.0000

Data Index: 410980 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1403903 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1036135 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.2176. Min Act: -0.0000

Data Index: 196430 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.1823. Min Act: -0.0000

Data Index: 1207645 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0684. Min Act: -0.0000

Data Index: 117287 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0518. Min Act: -0.0000

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.1645. Min Act: -0.0000

Data Index: 280200 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.1075. Min Act: -0.0000

Data Index: 1427241 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.1163. Min Act: -0.0000

Data Index: 1656073 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1170396 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1128524 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.9962. Min Act: -0.0000

Data Index: 1599139 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1133927 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1033363 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8329. Min Act: -0.0000

Data Index: 640622 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.9269. Min Act: -0.0000

Data Index: 596575 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8243. Min Act: -0.0000

Data Index: 1129990 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0281. Min Act: -0.0000

Data Index: 542065 (C4 (Web Text))

Max Activating Token Index: 209