Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2322. Min Range: -2.2322

Max Act: 2.2322. Min Act: -0.0000

Data Index: 997910 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.9728. Min Act: -0.0000

Data Index: 461262 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.2322. Min Range: -2.2322

Max Act: 2.0585. Min Act: -0.0000

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.2322. Min Range: -2.2322

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1005593 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.8127. Min Act: -0.0000

Data Index: 701141 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.7459. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1055186 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.8817. Min Act: -0.0000

Data Index: 313416 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.9083. Min Act: -0.0000

Data Index: 738034 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.7767. Min Act: -0.0000

Data Index: 525965 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.6160. Min Act: -0.0000

Data Index: 1038519 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.5995. Min Act: -0.0000

Data Index: 346398 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.5443. Min Act: -0.0000

Data Index: 94446 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.6238. Min Act: -0.0000

Data Index: 985699 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.6582. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.3344. Min Act: -0.0000

Data Index: 970695 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.4507. Min Act: -0.0000

Data Index: 427028 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1156494 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.5254. Min Act: -0.0000

Data Index: 868935 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 2.2322. Min Range: -2.2322

Max Act: 1.5040. Min Act: -0.0001

Data Index: 1128169 (C4 (Web Text))

Max Activating Token Index: 402