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

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

Neuron 1854 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: 1.3897. Min Range: -1.3897

Max Act: 1.3897. Min Act: -0.0000

Data Index: 300997 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.2027. Min Act: -0.0000

Data Index: 53170 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.2057. Min Act: -0.0000

Data Index: 732980 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.2423. Min Act: -0.0000

Data Index: 678381 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.2008. Min Act: -0.0000

Data Index: 571417 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1298357 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.1431. Min Act: 0.0000

Data Index: 1196410 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.1614. Min Act: -0.0000

Data Index: 415288 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.3897. Min Range: -1.3897

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1227317 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1089728 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.1916. Min Act: -0.0000

Data Index: 244203 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0815. Min Act: -0.0000

Data Index: 724345 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0758. Min Act: -0.0000

Data Index: 524422 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0694. Min Act: 0.0001

Data Index: 303280 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0045. Min Act: 0.0000

Data Index: 833763 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.1246. Min Act: -0.0000

Data Index: 581502 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0240. Min Act: -0.0000

Data Index: 174685 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0470. Min Act: -0.0000

Data Index: 383304 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1057407 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.3897. Min Range: -1.3897

Max Act: 1.0367. Min Act: 0.0001

Data Index: 1120785 (C4 (Web Text))

Max Activating Token Index: 323