Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0430. Min Act: -0.0001

Data Index: 55942 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1252327 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0408. Min Act: -0.0001

Data Index: 155795 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0389. Min Act: -0.0001

Data Index: 728217 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0411. Min Act: -0.0001

Data Index: 650738 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0370. Min Act: -0.0001

Data Index: 446481 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0363. Min Act: -0.0001

Data Index: 921796 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1458970 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0341. Min Act: -0.0001

Data Index: 485491 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1404100 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0406. Min Act: -0.0001

Data Index: 621395 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1480928 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0349. Min Act: -0.0001

Data Index: 349281 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1540318 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1160753 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0354. Min Act: -0.0001

Data Index: 56434 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0371. Min Act: -0.0001

Data Index: 703083 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0354. Min Act: -0.0001

Data Index: 166884 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0310. Min Act: -0.0001

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 413