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

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

Neuron 508 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: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0003

Data Index: 268780 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0335. Min Act: -0.0004

Data Index: 498511 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1211532 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1018837 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0319. Min Act: -0.0002

Data Index: 123820 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0296. Min Act: -0.0004

Data Index: 128479 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0291. Min Act: -0.0003

Data Index: 141941 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0257. Min Act: -0.0003

Data Index: 804629 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0267. Min Act: -0.0002

Data Index: 183794 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0252. Min Act: -0.0002

Data Index: 797788 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0250. Min Act: -0.0003

Data Index: 715533 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0245. Min Act: -0.0003

Data Index: 941125 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0243. Min Act: -0.0002

Data Index: 205789 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0243. Min Act: -0.0002

Data Index: 405308 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1102330 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0220. Min Act: -0.0003

Data Index: 547040 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0245. Min Act: -0.0003

Data Index: 923830 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0224. Min Act: -0.0003

Data Index: 371027 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1354392 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1294029 (C4 (Web Text))

Max Activating Token Index: 469