Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4187. Min Act: -0.0000

Data Index: 439898 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4005. Min Act: -0.0001

Data Index: 1202658 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4298. Min Act: -0.0001

Data Index: 165491 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3086. Min Act: -0.0000

Data Index: 276582 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3282. Min Act: -0.0001

Data Index: 677839 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3341. Min Act: -0.0000

Data Index: 93357 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1331975 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3177. Min Act: -0.0000

Data Index: 868831 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2651. Min Act: -0.0000

Data Index: 314295 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2929. Min Act: -0.0000

Data Index: 186858 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1091027 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2626. Min Act: -0.0001

Data Index: 768871 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2504. Min Act: -0.0000

Data Index: 146294 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1112554 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2322. Min Act: -0.0000

Data Index: 95248 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1054353 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3070. Min Act: -0.0000

Data Index: 104532 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2239. Min Act: -0.0000

Data Index: 45879 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2613. Min Act: -0.0001

Data Index: 1176517 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1069595 (C4 (Web Text))

Max Activating Token Index: 398