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

Dataset: The Pile

Neuron 4875 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: 1.2280. Min Range: -1.2280

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1798598 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1373041 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1246137 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0352. Min Act: 0.0000

Data Index: 138972 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1701497 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8428. Min Act: -0.0000

Data Index: 751175 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8312. Min Act: 0.0000

Data Index: 1018799 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1126546 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7203. Min Act: -0.0000

Data Index: 12490 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1302426 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1851742 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5882. Min Act: -0.0000

Data Index: 968506 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.6152. Min Act: -0.0000

Data Index: 280461 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1987562 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5100. Min Act: 0.0000

Data Index: 399181 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5295. Min Act: -0.0000

Data Index: 947205 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1363695 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1551075 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1230112 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.4896. Min Act: 0.0000

Data Index: 1722388 (The Pile)

Max Activating Token Index: 163