Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 326 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6921. Min Act: -0.0003

Data Index: 873355 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7141. Min Act: -0.0003

Data Index: 1338446 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7177. Min Act: -0.0003

Data Index: 567042 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7156. Min Act: -0.0003

Data Index: 433549 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7315. Min Act: -0.0003

Data Index: 839732 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6674. Min Act: -0.0003

Data Index: 595776 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6251. Min Act: -0.0003

Data Index: 831569 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7335. Min Act: -0.0003

Data Index: 941241 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5664. Min Act: -0.0003

Data Index: 1286817 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6552. Min Act: -0.0003

Data Index: 1156421 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7050. Min Act: -0.0003

Data Index: 1317201 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6523. Min Act: -0.0003

Data Index: 1252706 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6085. Min Act: -0.0003

Data Index: 181106 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6074. Min Act: -0.0003

Data Index: 341626 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6167. Min Act: -0.0003

Data Index: 967801 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6495. Min Act: -0.0003

Data Index: 506470 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6532. Min Act: -0.0003

Data Index: 1310157 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5686. Min Act: -0.0003

Data Index: 579454 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5953. Min Act: -0.0003

Data Index: 341725 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6046. Min Act: -0.0003

Data Index: 1012371 (C4 (Web Text))

Max Activating Token Index: 912