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

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

Neuron 105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.8278. Min Act: -0.0001

Data Index: 988226 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6652. Min Act: -0.0001

Data Index: 506421 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6024. Min Act: -0.0001

Data Index: 868571 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5391. Min Act: -0.0001

Data Index: 150352 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5325. Min Act: -0.0001

Data Index: 34434 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5533. Min Act: -0.0001

Data Index: 717473 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5049. Min Act: -0.0001

Data Index: 39750 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4760. Min Act: -0.0001

Data Index: 14056 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4519. Min Act: -0.0001

Data Index: 1557040 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4871. Min Act: -0.0001

Data Index: 868157 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4714. Min Act: -0.0001

Data Index: 713439 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5009. Min Act: -0.0001

Data Index: 115220 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4960. Min Act: -0.0001

Data Index: 1150937 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4781. Min Act: -0.0001

Data Index: 1289780 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4576. Min Act: -0.0001

Data Index: 175168 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4714. Min Act: -0.0001

Data Index: 566433 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4726. Min Act: -0.0001

Data Index: 562736 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4754. Min Act: -0.0001

Data Index: 1129342 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4580. Min Act: -0.0001

Data Index: 1354062 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1299090 (C4 (Web Text))

Max Activating Token Index: 466