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

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

Neuron 4762 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1259638 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1210847 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0634. Min Act: -0.0000

Data Index: 619293 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0581. Min Act: -0.0000

Data Index: 883937 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0573. Min Act: -0.0000

Data Index: 648593 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1595637 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1343212 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0492. Min Act: -0.0000

Data Index: 946252 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0462. Min Act: -0.0000

Data Index: 173985 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1406161 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0462. Min Act: -0.0000

Data Index: 725418 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0494. Min Act: -0.0000

Data Index: 188770 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0509. Min Act: -0.0000

Data Index: 485628 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0475. Min Act: -0.0000

Data Index: 526057 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0490. Min Act: -0.0000

Data Index: 538109 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0475. Min Act: -0.0000

Data Index: 279066 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0484. Min Act: -0.0000

Data Index: 313163 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1639126 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0441. Min Act: -0.0000

Data Index: 874020 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1588853 (Python Code)

Max Activating Token Index: 443