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

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

Neuron 4340 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.9614. Min Act: -0.0000

Data Index: 221378 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 2.0319. Min Range: -2.0319

Max Act: 2.0319. Min Act: -0.0000

Data Index: 881001 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.9171. Min Act: -0.0000

Data Index: 26881 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.7935. Min Act: -0.0000

Data Index: 428313 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.8698. Min Act: -0.0000

Data Index: 162232 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.9170. Min Act: -0.0000

Data Index: 1283596 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.7455. Min Act: -0.0000

Data Index: 761796 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.6621. Min Act: -0.0000

Data Index: 856434 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.3968. Min Act: -0.0000

Data Index: 391358 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5506. Min Act: -0.0000

Data Index: 132652 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1247735 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5228. Min Act: -0.0000

Data Index: 1177116 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1048099 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5587. Min Act: -0.0000

Data Index: 725726 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5252. Min Act: -0.0000

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.4424. Min Act: -0.0000

Data Index: 348952 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.4320. Min Act: -0.0000

Data Index: 46593 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.3365. Min Act: -0.0000

Data Index: 118149 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.5740. Min Act: -0.0000

Data Index: 966921 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 2.0319. Min Range: -2.0319

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1028271 (C4 (Web Text))

Max Activating Token Index: 767