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

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

Neuron 3297 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3040. Min Act: -0.0000

Data Index: 826423 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1278499 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2753. Min Act: -0.0000

Data Index: 870238 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2754. Min Act: -0.0000

Data Index: 621731 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2700. Min Act: -0.0000

Data Index: 986520 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2438. Min Act: -0.0000

Data Index: 206212 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2401. Min Act: -0.0000

Data Index: 714279 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2300. Min Act: -0.0000

Data Index: 380298 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2384. Min Act: -0.0000

Data Index: 238041 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2539. Min Act: -0.0000

Data Index: 79926 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1336253 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1069647 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2389. Min Act: -0.0000

Data Index: 789234 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2364. Min Act: -0.0000

Data Index: 961022 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2286. Min Act: -0.0000

Data Index: 716893 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2340. Min Act: -0.0000

Data Index: 582523 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1301039 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2195. Min Act: -0.0000

Data Index: 179180 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1077178 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2094. Min Act: -0.0000

Data Index: 8394 (C4 (Web Text))

Max Activating Token Index: 418