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

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

Neuron 4785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.7218. Min Act: -0.0000

Data Index: 732498 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6874. Min Act: -0.0000

Data Index: 651279 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6699. Min Act: -0.0000

Data Index: 472717 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6584. Min Act: -0.0000

Data Index: 623158 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1102807 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6297. Min Act: -0.0000

Data Index: 444861 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6278. Min Act: -0.0000

Data Index: 959018 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1286268 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1310760 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6365. Min Act: -0.0000

Data Index: 626785 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1210562 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6319. Min Act: -0.0000

Data Index: 450880 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6288. Min Act: -0.0000

Data Index: 23207 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6260. Min Act: -0.0000

Data Index: 281552 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1300642 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6502. Min Act: -0.0001

Data Index: 690001 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.5857. Min Act: -0.0000

Data Index: 588680 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6427. Min Act: -0.0000

Data Index: 966614 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6852. Min Act: -0.0000

Data Index: 928191 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.7218. Min Range: -0.7218

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1284339 (C4 (Web Text))

Max Activating Token Index: 350