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

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

Neuron 941 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0003

Data Index: 724957 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0390. Min Act: -0.0003

Data Index: 736304 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1537380 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0332. Min Act: -0.0003

Data Index: 27979 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0307. Min Act: -0.0003

Data Index: 348279 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1270515 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1412404 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1509236 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0326. Min Act: -0.0004

Data Index: 946132 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1000385 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0309. Min Act: -0.0003

Data Index: 471219 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1358008 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1538891 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0315. Min Act: -0.0003

Data Index: 895746 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1534510 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0312. Min Act: -0.0003

Data Index: 960855 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1505635 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0315. Min Act: -0.0003

Data Index: 986704 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0307. Min Act: -0.0003

Data Index: 272558 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0315. Min Act: -0.0003

Data Index: 71915 (C4 (Web Text))

Max Activating Token Index: 525