Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 721 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1076952 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0345. Min Act: -0.0003

Data Index: 837272 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0346. Min Act: -0.0002

Data Index: 921901 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0002

Data Index: 365189 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0339. Min Act: -0.0002

Data Index: 229328 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1073427 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0335. Min Act: -0.0002

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0329. Min Act: -0.0002

Data Index: 105320 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: -0.0003

Data Index: 85415 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0319. Min Act: -0.0003

Data Index: 601768 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0319. Min Act: -0.0003

Data Index: 111620 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1341316 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0303. Min Act: -0.0003

Data Index: 583211 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1138725 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0298. Min Act: -0.0003

Data Index: 127624 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0295. Min Act: -0.0002

Data Index: 551679 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0289. Min Act: -0.0003

Data Index: 743579 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0285. Min Act: -0.0003

Data Index: 174758 (C4 (Web Text))

Max Activating Token Index: 562