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

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

Neuron 1631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6860. Min Act: -0.0000

Data Index: 324353 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5924. Min Act: -0.0000

Data Index: 523485 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1215976 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5179. Min Act: -0.0000

Data Index: 248906 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4884. Min Act: -0.0000

Data Index: 642236 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4762. Min Act: -0.0000

Data Index: 461464 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4610. Min Act: -0.0000

Data Index: 855778 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4278. Min Act: -0.0000

Data Index: 677614 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4430. Min Act: -0.0000

Data Index: 310019 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1104480 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1194191 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3795. Min Act: -0.0000

Data Index: 380712 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4166. Min Act: -0.0000

Data Index: 147641 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3875. Min Act: -0.0000

Data Index: 175617 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1308626 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3693. Min Act: -0.0000

Data Index: 749357 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3865. Min Act: -0.0000

Data Index: 435095 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3663. Min Act: -0.0000

Data Index: 966959 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3586. Min Act: -0.0000

Data Index: 249853 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3559. Min Act: -0.0000

Data Index: 822093 (C4 (Web Text))

Max Activating Token Index: 788