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

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

Neuron 333 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: 0.2242. Min Range: -0.2242

Max Act: 0.2242. Min Act: -0.0000

Data Index: 453891 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2204. Min Act: -0.0000

Data Index: 4324 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2150. Min Act: -0.0000

Data Index: 730394 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1206503 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2055. Min Act: -0.0000

Data Index: 538258 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1015843 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1220003 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1883. Min Act: -0.0000

Data Index: 620500 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1932. Min Act: -0.0000

Data Index: 693586 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1342214 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1092027 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1819. Min Act: -0.0000

Data Index: 591792 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1883. Min Act: -0.0000

Data Index: 112912 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1738. Min Act: -0.0000

Data Index: 994020 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1795. Min Act: -0.0000

Data Index: 292325 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1720. Min Act: -0.0000

Data Index: 781792 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1830. Min Act: -0.0000

Data Index: 668054 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1293744 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1679. Min Act: -0.0000

Data Index: 954787 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1681. Min Act: -0.0000

Data Index: 108458 (C4 (Web Text))

Max Activating Token Index: 661