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

Dataset: The Pile

Neuron 962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1923042 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1624898 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0231. Min Act: -0.0000

Data Index: 527848 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1778829 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9362. Min Act: 0.0000

Data Index: 1578365 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1621432 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1684165 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9231. Min Act: -0.0000

Data Index: 708581 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1337490 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1534269 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1095473 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9202. Min Act: -0.0000

Data Index: 246733 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1271274 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8524. Min Act: -0.0000

Data Index: 418488 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8406. Min Act: -0.0000

Data Index: 296063 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1139962 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8580. Min Act: -0.0000

Data Index: 628063 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8326. Min Act: -0.0000

Data Index: 434751 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8339. Min Act: -0.0000

Data Index: 212184 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8369. Min Act: -0.0000

Data Index: 251343 (The Pile)

Max Activating Token Index: 149