Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0003

Data Index: 46155 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1347906 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0380. Min Act: -0.0003

Data Index: 997880 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0370. Min Act: -0.0003

Data Index: 628442 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0397. Min Act: -0.0003

Data Index: 987764 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0368. Min Act: -0.0003

Data Index: 883558 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1153016 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0322. Min Act: -0.0003

Data Index: 613041 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1011347 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0304. Min Act: -0.0003

Data Index: 750656 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1146738 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0303. Min Act: -0.0003

Data Index: 668189 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0288. Min Act: -0.0003

Data Index: 3575 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1286022 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0261. Min Act: -0.0003

Data Index: 750286 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1505748 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0273. Min Act: -0.0003

Data Index: 203646 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0266. Min Act: -0.0003

Data Index: 8330 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0266. Min Act: -0.0003

Data Index: 586406 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0245. Min Act: -0.0003

Data Index: 346987 (C4 (Web Text))

Max Activating Token Index: 573