Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2554 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0298. Min Range: -1.0298

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1434683 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 1.0298. Min Range: -1.0298

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1424132 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1094448 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1296887 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.9528. Min Act: -0.0000

Data Index: 740122 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1135029 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1539659 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8210. Min Act: -0.0000

Data Index: 25277 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7920. Min Act: -0.0000

Data Index: 917825 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1305584 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1647058 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8253. Min Act: -0.0000

Data Index: 448893 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8405. Min Act: -0.0000

Data Index: 80300 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1386499 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1592132 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1112159 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8022. Min Act: -0.0000

Data Index: 238419 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7299. Min Act: -0.0000

Data Index: 730489 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.8221. Min Act: -0.0000

Data Index: 860141 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.0298. Min Range: -1.0298

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1423481 (Python Code)

Max Activating Token Index: 268