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

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

Neuron 1269 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.6200. Min Act: -0.0001

Data Index: 418943 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4314. Min Act: -0.0001

Data Index: 359625 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3969. Min Act: -0.0001

Data Index: 883408 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3723. Min Act: -0.0001

Data Index: 649360 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3665. Min Act: -0.0001

Data Index: 430318 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1148973 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3674. Min Act: -0.0001

Data Index: 389482 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3695. Min Act: -0.0001

Data Index: 336080 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1359849 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3851. Min Act: -0.0001

Data Index: 624784 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3456. Min Act: -0.0001

Data Index: 164428 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3492. Min Act: -0.0001

Data Index: 905648 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3800. Min Act: -0.0001

Data Index: 952524 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3524. Min Act: -0.0001

Data Index: 361809 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3255. Min Act: -0.0001

Data Index: 235928 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3441. Min Act: -0.0001

Data Index: 348055 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1231527 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1537529 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3216. Min Act: -0.0001

Data Index: 703565 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3210. Min Act: -0.0001

Data Index: 705810 (C4 (Web Text))

Max Activating Token Index: 331