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

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

Neuron 5147 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: 0.1956. Min Range: -0.1956

Max Act: 0.1956. Min Act: -0.0000

Data Index: 949896 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1924. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1727. Min Act: -0.0000

Data Index: 445104 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1717. Min Act: -0.0000

Data Index: 31690 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1461. Min Act: -0.0000

Data Index: 686874 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1501. Min Act: -0.0000

Data Index: 915854 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1458. Min Act: -0.0000

Data Index: 280615 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1389. Min Act: -0.0000

Data Index: 284339 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1341. Min Act: -0.0000

Data Index: 378524 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1298. Min Act: -0.0000

Data Index: 679240 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1173. Min Act: -0.0000

Data Index: 109793 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1192. Min Act: -0.0000

Data Index: 586437 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1183. Min Act: -0.0000

Data Index: 569597 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1168. Min Act: -0.0000

Data Index: 74516 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1176. Min Act: -0.0000

Data Index: 71629 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1120. Min Act: -0.0000

Data Index: 295772 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1114. Min Act: -0.0000

Data Index: 387899 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1097. Min Act: -0.0000

Data Index: 57730 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1082. Min Act: -0.0000

Data Index: 598095 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1103. Min Act: -0.0000

Data Index: 539166 (C4 (Web Text))

Max Activating Token Index: 48