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

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

Neuron 594 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0006

Data Index: 236376 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0511. Min Act: -0.0006

Data Index: 187147 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0441. Min Act: -0.0005

Data Index: 1316054 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0439. Min Act: -0.0005

Data Index: 239631 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0425. Min Act: -0.0005

Data Index: 940978 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0430. Min Act: -0.0005

Data Index: 29257 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0418. Min Act: -0.0005

Data Index: 53709 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0413. Min Act: -0.0005

Data Index: 961462 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0404. Min Act: -0.0006

Data Index: 626177 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1370363 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0423. Min Act: -0.0006

Data Index: 569915 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0368. Min Act: -0.0005

Data Index: 571391 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0375. Min Act: -0.0006

Data Index: 219169 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0349. Min Act: -0.0006

Data Index: 615228 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0367. Min Act: -0.0006

Data Index: 575830 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0350. Min Act: -0.0005

Data Index: 432112 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0328. Min Act: -0.0006

Data Index: 330183 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0346. Min Act: -0.0005

Data Index: 992137 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0339. Min Act: -0.0006

Data Index: 72740 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0337. Min Act: -0.0005

Data Index: 544759 (C4 (Web Text))

Max Activating Token Index: 434