Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5148 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3580. Min Act: -0.0001

Data Index: 1063782 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1094 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1483605 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1256678 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2668. Min Act: -0.0000

Data Index: 905120 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2639. Min Act: -0.0001

Data Index: 127230 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1303887 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2542. Min Act: -0.0001

Data Index: 708169 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2537. Min Act: -0.0001

Data Index: 86480 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2074. Min Act: -0.0001

Data Index: 200402 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2175. Min Act: -0.0001

Data Index: 187802 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1304395 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2595. Min Act: -0.0001

Data Index: 155787 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2296. Min Act: -0.0001

Data Index: 830733 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2366. Min Act: -0.0000

Data Index: 970103 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1280757 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1547829 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1340754 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2399. Min Act: -0.0001

Data Index: 160307 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1133133 (C4 (Web Text))

Max Activating Token Index: 735