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

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

Neuron 1141 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: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0005

Data Index: 1213182 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0474. Min Act: -0.0005

Data Index: 72048 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0445. Min Act: -0.0005

Data Index: 364832 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1067604 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0404. Min Act: -0.0005

Data Index: 455565 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0421. Min Act: -0.0005

Data Index: 197221 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0429. Min Act: -0.0005

Data Index: 737620 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0384. Min Act: -0.0005

Data Index: 1178218 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0450. Min Act: -0.0005

Data Index: 1073373 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0407. Min Act: -0.0005

Data Index: 342187 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1223418 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0371. Min Act: -0.0005

Data Index: 266252 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0392. Min Act: -0.0005

Data Index: 762838 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0388. Min Act: -0.0005

Data Index: 432984 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0381. Min Act: -0.0005

Data Index: 541067 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0381. Min Act: -0.0005

Data Index: 38778 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0373. Min Act: -0.0005

Data Index: 1002330 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0397. Min Act: -0.0005

Data Index: 586423 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1182289 (C4 (Web Text))

Max Activating Token Index: 537