Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1254 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1560992 (Python Code)

Max Activating Token Index: 500

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1633535 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0393. Min Act: -0.0003

Data Index: 358471 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1515176 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1366318 (Python Code)

Max Activating Token Index: 589

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1584268 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1407930 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1614231 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0322. Min Act: -0.0003

Data Index: 951761 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0308. Min Act: -0.0003

Data Index: 238028 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1601623 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1322944 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1452740 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1309768 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0284. Min Act: -0.0003

Data Index: 42042 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0272. Min Act: -0.0003

Data Index: 220558 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1240667 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1651079 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0277. Min Act: -0.0003

Data Index: 216008 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1382177 (Python Code)

Max Activating Token Index: 389