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

Dataset: The Pile

Neuron 1344 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1891857 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4427. Min Act: -0.0000

Data Index: 75934 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1713773 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1055451 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3593. Min Act: -0.0000

Data Index: 43940 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4087. Min Act: -0.0000

Data Index: 503361 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1367038 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1560328 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3459. Min Act: -0.0000

Data Index: 487816 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3354. Min Act: -0.0000

Data Index: 688709 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3296. Min Act: -0.0000

Data Index: 982504 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1935118 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3414. Min Act: -0.0000

Data Index: 541092 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3237. Min Act: -0.0000

Data Index: 830188 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1258059 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1570127 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1132741 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3241. Min Act: -0.0000

Data Index: 306689 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1548883 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1199335 (The Pile)

Max Activating Token Index: 581