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

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

Neuron 3389 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: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0003

Data Index: 818590 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1612588 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1628055 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1383656 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1462135 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1601486 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1534945 (Python Code)

Max Activating Token Index: 684

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0281. Min Act: -0.0003

Data Index: 136036 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1629537 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1527180 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0279. Min Act: -0.0003

Data Index: 638850 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1520829 (Python Code)

Max Activating Token Index: 106

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1544867 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1531185 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1623576 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1536990 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1392604 (Python Code)

Max Activating Token Index: 156

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1478985 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0266. Min Act: -0.0003

Data Index: 511188 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1405997 (Python Code)

Max Activating Token Index: 805