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

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

Neuron 4886 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: 1.3404. Min Range: -1.3404

Max Act: 1.3404. Min Act: -0.0000

Data Index: 992118 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.3033. Min Act: -0.0000

Data Index: 22447 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.2302. Min Act: -0.0000

Data Index: 52432 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1720. Min Act: -0.0000

Data Index: 776692 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1136. Min Act: -0.0000

Data Index: 641354 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1507. Min Act: -0.0000

Data Index: 816662 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.2190. Min Act: -0.0000

Data Index: 993999 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1341. Min Act: -0.0000

Data Index: 628660 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0927. Min Act: -0.0000

Data Index: 556878 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0340. Min Act: -0.0000

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1491. Min Act: -0.0000

Data Index: 20498 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0501. Min Act: -0.0000

Data Index: 978296 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9375. Min Act: -0.0000

Data Index: 814868 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1208223 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9753. Min Act: -0.0000

Data Index: 278560 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1016427 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1334804 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1090425 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8637. Min Act: -0.0000

Data Index: 780427 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9036. Min Act: -0.0000

Data Index: 571058 (C4 (Web Text))

Max Activating Token Index: 644