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

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

Neuron 2536 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1335960 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2723. Min Act: -0.0000

Data Index: 80502 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1324900 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2742. Min Act: -0.0000

Data Index: 781878 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2601. Min Act: -0.0000

Data Index: 211064 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2708. Min Act: -0.0000

Data Index: 659625 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2470. Min Act: -0.0000

Data Index: 368500 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2573. Min Act: -0.0000

Data Index: 891516 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2373. Min Act: -0.0000

Data Index: 640525 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2219. Min Act: -0.0000

Data Index: 716521 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2293. Min Act: -0.0000

Data Index: 253444 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2119. Min Act: -0.0000

Data Index: 837798 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1213488 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2056. Min Act: -0.0000

Data Index: 549384 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2152. Min Act: -0.0000

Data Index: 694322 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2140. Min Act: -0.0000

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2063. Min Act: -0.0000

Data Index: 595773 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2138. Min Act: -0.0000

Data Index: 868043 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2048. Min Act: -0.0000

Data Index: 14901 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1912. Min Act: -0.0000

Data Index: 45122 (C4 (Web Text))

Max Activating Token Index: 209