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

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

Neuron 108 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0001

Data Index: 388747 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1198968 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1659. Min Act: -0.0001

Data Index: 867921 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1158934 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1327514 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1661. Min Act: -0.0001

Data Index: 106875 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1603. Min Act: -0.0001

Data Index: 447126 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1561. Min Act: -0.0001

Data Index: 592121 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1061746 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1534. Min Act: -0.0001

Data Index: 183747 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1106875 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1286. Min Act: -0.0001

Data Index: 396419 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1354548 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1306. Min Act: -0.0001

Data Index: 460132 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1249. Min Act: -0.0001

Data Index: 606928 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1285. Min Act: -0.0001

Data Index: 321398 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1267. Min Act: -0.0001

Data Index: 530523 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1411. Min Act: -0.0001

Data Index: 163345 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1187. Min Act: -0.0001

Data Index: 279089 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1301. Min Act: -0.0001

Data Index: 948541 (C4 (Web Text))

Max Activating Token Index: 227