Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1673823 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.5295. Min Act: -0.0000

Data Index: 505945 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1484251 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1609056 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1866070 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1351969 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1480227 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0493. Min Act: -0.0000

Data Index: 305929 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1499221 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1315362 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1180625 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0385. Min Act: -0.0000

Data Index: 588356 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1764171 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1142842 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1308105 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9612. Min Act: -0.0000

Data Index: 530016 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9842. Min Act: -0.0000

Data Index: 309287 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1077508 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1611894 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1182396 (The Pile)

Max Activating Token Index: 887