Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0005

Data Index: 848327 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0432. Min Act: -0.0005

Data Index: 562666 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0394. Min Act: -0.0005

Data Index: 1076826 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0379. Min Act: -0.0005

Data Index: 409492 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0375. Min Act: -0.0005

Data Index: 155562 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0362. Min Act: -0.0005

Data Index: 1267203 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0364. Min Act: -0.0005

Data Index: 699358 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0369. Min Act: -0.0005

Data Index: 567779 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1359450 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0344. Min Act: -0.0005

Data Index: 87470 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0350. Min Act: -0.0005

Data Index: 1041163 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0343. Min Act: -0.0005

Data Index: 857942 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0345. Min Act: -0.0005

Data Index: 787609 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1141201 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0342. Min Act: -0.0005

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1045651 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0332. Min Act: -0.0005

Data Index: 634196 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0340. Min Act: -0.0005

Data Index: 235694 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1139496 (C4 (Web Text))

Max Activating Token Index: 941