Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0006

Data Index: 147803 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0355. Min Act: -0.0006

Data Index: 705548 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0354. Min Act: -0.0006

Data Index: 817821 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0346. Min Act: -0.0006

Data Index: 424443 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0326. Min Act: -0.0006

Data Index: 208367 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0311. Min Act: -0.0006

Data Index: 87359 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0310. Min Act: -0.0006

Data Index: 826547 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0310. Min Act: -0.0005

Data Index: 1016682 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0307. Min Act: -0.0006

Data Index: 942093 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1292102 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0304. Min Act: -0.0006

Data Index: 155337 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0292. Min Act: -0.0006

Data Index: 472863 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0290. Min Act: -0.0006

Data Index: 484625 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0277. Min Act: -0.0006

Data Index: 810747 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0302. Min Act: -0.0006

Data Index: 989371 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0282. Min Act: -0.0006

Data Index: 366311 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0290. Min Act: -0.0006

Data Index: 293569 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0282. Min Act: -0.0006

Data Index: 834775 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0275. Min Act: -0.0006

Data Index: 493592 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0269. Min Act: -0.0006

Data Index: 979288 (C4 (Web Text))

Max Activating Token Index: 594