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

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

Neuron 3921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0428. Min Act: -0.0001

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0348. Min Act: -0.0001

Data Index: 753088 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0284. Min Act: -0.0001

Data Index: 276073 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0337. Min Act: -0.0002

Data Index: 894808 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0332. Min Act: -0.0001

Data Index: 535186 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1287789 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0341. Min Act: -0.0002

Data Index: 494002 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0305. Min Act: -0.0002

Data Index: 260892 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1288200 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1573015 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0317. Min Act: -0.0002

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1126570 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1269821 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0295. Min Act: -0.0002

Data Index: 727846 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0218. Min Act: -0.0002

Data Index: 758943 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0311. Min Act: -0.0002

Data Index: 724273 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0285. Min Act: -0.0001

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0298. Min Act: -0.0002

Data Index: 615454 (C4 (Web Text))

Max Activating Token Index: 691