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

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

Neuron 240 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: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0005

Data Index: 82205 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1197975 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0408. Min Act: -0.0005

Data Index: 990805 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0368. Min Act: -0.0005

Data Index: 170543 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0384. Min Act: -0.0005

Data Index: 640422 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1106089 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0400. Min Act: -0.0005

Data Index: 830828 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0393. Min Act: -0.0005

Data Index: 3349 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1132258 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0399. Min Act: -0.0005

Data Index: 42804 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0384. Min Act: -0.0005

Data Index: 751032 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0385. Min Act: -0.0005

Data Index: 926204 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0381. Min Act: -0.0005

Data Index: 888590 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0395. Min Act: -0.0005

Data Index: 307998 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0369. Min Act: -0.0005

Data Index: 674034 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0370. Min Act: -0.0005

Data Index: 626890 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0388. Min Act: -0.0005

Data Index: 224795 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0371. Min Act: -0.0005

Data Index: 408417 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0369. Min Act: -0.0005

Data Index: 424144 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1244445 (C4 (Web Text))

Max Activating Token Index: 666