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

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

Neuron 553 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: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0006

Data Index: 295538 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0329. Min Act: -0.0006

Data Index: 793267 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0300. Min Act: -0.0006

Data Index: 304149 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0302. Min Act: -0.0006

Data Index: 378402 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1243899 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0301. Min Act: -0.0006

Data Index: 668222 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0294. Min Act: -0.0006

Data Index: 961400 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1111340 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0296. Min Act: -0.0006

Data Index: 409487 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0300. Min Act: -0.0006

Data Index: 179166 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0294. Min Act: -0.0006

Data Index: 792784 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0291. Min Act: -0.0005

Data Index: 704860 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0297. Min Act: -0.0006

Data Index: 205786 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0298. Min Act: -0.0006

Data Index: 452708 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0290. Min Act: -0.0006

Data Index: 840120 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1206955 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0288. Min Act: -0.0006

Data Index: 859468 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1144584 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0293. Min Act: -0.0006

Data Index: 621843 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0282. Min Act: -0.0006

Data Index: 887405 (C4 (Web Text))

Max Activating Token Index: 672