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

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

Neuron 1323 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: 1.2063. Min Range: -1.2063

Max Act: 1.2063. Min Act: -0.0001

Data Index: 163506 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.9677. Min Act: -0.0001

Data Index: 631571 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.9023. Min Act: -0.0001

Data Index: 369207 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8146. Min Act: -0.0001

Data Index: 1346622 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8433. Min Act: -0.0001

Data Index: 173995 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7991. Min Act: -0.0001

Data Index: 319343 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8483. Min Act: -0.0001

Data Index: 1141697 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1191799 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8110. Min Act: -0.0001

Data Index: 360990 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8331. Min Act: -0.0001

Data Index: 686642 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8193. Min Act: -0.0001

Data Index: 572346 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7622. Min Act: -0.0001

Data Index: 649154 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7844. Min Act: -0.0001

Data Index: 829267 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1038939 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7785. Min Act: -0.0001

Data Index: 11126 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7250. Min Act: -0.0001

Data Index: 1179370 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7526. Min Act: -0.0001

Data Index: 592248 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1346168 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7449. Min Act: -0.0001

Data Index: 909930 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.2063. Min Range: -1.2063

Max Act: 0.7600. Min Act: -0.0001

Data Index: 942971 (C4 (Web Text))

Max Activating Token Index: 1020