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

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

Neuron 1808 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: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0005

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0555. Min Act: -0.0005

Data Index: 83026 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1215478 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0502. Min Act: -0.0005

Data Index: 182209 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0466. Min Act: -0.0005

Data Index: 424695 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0489. Min Act: -0.0005

Data Index: 998995 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0466. Min Act: -0.0005

Data Index: 915078 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0453. Min Act: -0.0005

Data Index: 624592 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0409. Min Act: -0.0005

Data Index: 695244 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0460. Min Act: -0.0005

Data Index: 274506 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0436. Min Act: -0.0005

Data Index: 1164518 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0453. Min Act: -0.0005

Data Index: 928864 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0435. Min Act: -0.0005

Data Index: 964280 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0435. Min Act: -0.0005

Data Index: 858321 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0415. Min Act: -0.0005

Data Index: 767284 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0444. Min Act: -0.0005

Data Index: 1190021 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0431. Min Act: -0.0005

Data Index: 398892 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0425. Min Act: -0.0005

Data Index: 548891 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0413. Min Act: -0.0005

Data Index: 1335401 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0425. Min Act: -0.0005

Data Index: 607335 (C4 (Web Text))

Max Activating Token Index: 751