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

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

Neuron 3935 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1654. Min Act: -0.0002

Data Index: 822042 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1552. Min Act: -0.0002

Data Index: 630743 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1534. Min Act: -0.0002

Data Index: 1021165 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1475. Min Act: -0.0002

Data Index: 184900 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1494. Min Act: -0.0002

Data Index: 670830 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1421. Min Act: -0.0002

Data Index: 23686 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1504. Min Act: -0.0002

Data Index: 599358 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1371. Min Act: -0.0002

Data Index: 840616 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1411. Min Act: -0.0002

Data Index: 829889 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1312. Min Act: -0.0002

Data Index: 329210 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1303. Min Act: -0.0002

Data Index: 481593 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1308. Min Act: -0.0002

Data Index: 447822 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1245. Min Act: -0.0002

Data Index: 928297 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1268. Min Act: -0.0002

Data Index: 346926 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1229. Min Act: -0.0002

Data Index: 38498 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1205. Min Act: -0.0002

Data Index: 273811 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1253198 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1260. Min Act: -0.0002

Data Index: 684486 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1292. Min Act: -0.0002

Data Index: 242837 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1299. Min Act: -0.0002

Data Index: 505399 (C4 (Web Text))

Max Activating Token Index: 68