Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2508 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.1086. Min Act: -0.0000

Data Index: 842446 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9834. Min Act: -0.0000

Data Index: 874249 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.0228. Min Act: -0.0000

Data Index: 211264 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9647. Min Act: -0.0000

Data Index: 343085 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9924. Min Act: -0.0000

Data Index: 354595 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9704. Min Act: -0.0000

Data Index: 937449 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9173. Min Act: -0.0000

Data Index: 676179 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9115. Min Act: -0.0000

Data Index: 745444 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8803. Min Act: -0.0000

Data Index: 521572 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8644. Min Act: -0.0000

Data Index: 145302 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1156124 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8482. Min Act: -0.0000

Data Index: 789865 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7951. Min Act: -0.0000

Data Index: 107963 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8157. Min Act: -0.0000

Data Index: 105658 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8372. Min Act: -0.0000

Data Index: 213639 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8077. Min Act: -0.0000

Data Index: 912489 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1034614 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7687. Min Act: -0.0000

Data Index: 328623 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7629. Min Act: -0.0000

Data Index: 600065 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7527. Min Act: -0.0000

Data Index: 3271 (C4 (Web Text))

Max Activating Token Index: 750