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

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

Neuron 3105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0002

Data Index: 630245 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0412. Min Act: -0.0002

Data Index: 950405 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0424. Min Act: -0.0002

Data Index: 661865 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1143136 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0386. Min Act: -0.0002

Data Index: 485556 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1299106 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1152779 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0382. Min Act: -0.0002

Data Index: 331840 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0380. Min Act: -0.0002

Data Index: 732797 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0363. Min Act: -0.0002

Data Index: 670990 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0407. Min Act: -0.0002

Data Index: 203340 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1148771 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0399. Min Act: -0.0002

Data Index: 90598 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1072501 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0361. Min Act: -0.0002

Data Index: 876020 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1352966 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1179456 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1266284 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0396. Min Act: -0.0002

Data Index: 502506 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0365. Min Act: -0.0002

Data Index: 741182 (C4 (Web Text))

Max Activating Token Index: 340