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

Dataset: The Pile

Neuron 43 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: 0.5096. Min Range: -0.5096

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1836546 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.5096. Min Act: -0.0000

Data Index: 624900 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4209. Min Act: -0.0000

Data Index: 537620 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1607179 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1530196 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3668. Min Act: -0.0000

Data Index: 742956 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1420156 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3710. Min Act: -0.0000

Data Index: 675512 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3258. Min Act: -0.0000

Data Index: 346565 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3583. Min Act: -0.0000

Data Index: 306023 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1609459 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1257669 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3349. Min Act: -0.0000

Data Index: 530685 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1238653 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3411. Min Act: -0.0000

Data Index: 112923 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1888842 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3284. Min Act: -0.0000

Data Index: 298000 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1139264 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1366209 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1392706 (The Pile)

Max Activating Token Index: 178