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

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

Neuron 1113 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4894. Min Range: -7.4894

Max Act: 7.4894. Min Act: -0.0000

Data Index: 1202637 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 7.4894. Min Range: -7.4894

Max Act: 7.1413. Min Act: -0.0000

Data Index: 332389 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.9717. Min Act: -0.0000

Data Index: 747324 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.6351. Min Act: -0.0000

Data Index: 316737 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.3322. Min Act: -0.0000

Data Index: 907926 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.6705. Min Act: -0.0000

Data Index: 411603 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.1599. Min Act: -0.0000

Data Index: 680113 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.2437. Min Act: -0.0000

Data Index: 336442 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.2324. Min Act: -0.0000

Data Index: 669022 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.7867. Min Act: -0.0000

Data Index: 1333205 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.1477. Min Act: -0.0000

Data Index: 789112 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.7205. Min Act: -0.0000

Data Index: 1266082 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.0981. Min Act: -0.0000

Data Index: 339953 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.8929. Min Act: -0.0000

Data Index: 1010472 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 7.4894. Min Range: -7.4894

Max Act: 6.0177. Min Act: -0.0000

Data Index: 853212 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.7875. Min Act: -0.0000

Data Index: 474175 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.7681. Min Act: -0.0000

Data Index: 130756 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.9272. Min Act: -0.0000

Data Index: 547984 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.7036. Min Act: -0.0000

Data Index: 783096 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 7.4894. Min Range: -7.4894

Max Act: 5.8877. Min Act: -0.0000

Data Index: 1061520 (C4 (Web Text))

Max Activating Token Index: 31