Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3574 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1200116 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0491. Min Act: -0.0003

Data Index: 435877 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1086619 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0444. Min Act: -0.0003

Data Index: 825233 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0415. Min Act: -0.0003

Data Index: 857000 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0410. Min Act: -0.0003

Data Index: 333008 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1634995 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0464. Min Act: -0.0003

Data Index: 547759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1164672 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0424. Min Act: -0.0003

Data Index: 444304 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0427. Min Act: -0.0003

Data Index: 536250 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1158356 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0398. Min Act: -0.0003

Data Index: 614722 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0447. Min Act: -0.0003

Data Index: 68952 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1045435 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0411. Min Act: -0.0003

Data Index: 428247 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0425. Min Act: -0.0003

Data Index: 895343 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0472. Min Act: -0.0003

Data Index: 892021 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1607256 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0434. Min Act: -0.0003

Data Index: 143150 (C4 (Web Text))

Max Activating Token Index: 864