Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 197 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0006

Data Index: 1021409 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0451. Min Act: -0.0006

Data Index: 94272 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0448. Min Act: -0.0006

Data Index: 916771 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0420. Min Act: -0.0006

Data Index: 294343 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0413. Min Act: -0.0006

Data Index: 712344 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0429. Min Act: -0.0006

Data Index: 983598 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0418. Min Act: -0.0006

Data Index: 85783 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0406. Min Act: -0.0006

Data Index: 134315 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1239616 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1168406 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0006

Data Index: 905209 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0387. Min Act: -0.0006

Data Index: 684145 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0388. Min Act: -0.0006

Data Index: 615533 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0394. Min Act: -0.0006

Data Index: 1227175 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0402. Min Act: -0.0006

Data Index: 579666 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0383. Min Act: -0.0006

Data Index: 380841 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0380. Min Act: -0.0006

Data Index: 184643 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0403. Min Act: -0.0006

Data Index: 798011 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0391. Min Act: -0.0006

Data Index: 503930 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0381. Min Act: -0.0006

Data Index: 745488 (C4 (Web Text))

Max Activating Token Index: 123