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

Dataset: The Pile

Neuron 166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7931. Min Act: -0.0000

Data Index: 835927 (The Pile)

Max Activating Token Index: 217

Text #1

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7471. Min Act: -0.0000

Data Index: 816475 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7270. Min Act: -0.0000

Data Index: 72097 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1915502 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7501. Min Act: -0.0000

Data Index: 554967 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7187. Min Act: -0.0000

Data Index: 270324 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1193719 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1218556 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1250769 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1263030 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6318. Min Act: -0.0000

Data Index: 725750 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1101859 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1791426 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6310. Min Act: -0.0000

Data Index: 715890 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1197608 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1931814 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6820. Min Act: -0.0000

Data Index: 328956 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7068. Min Act: -0.0000

Data Index: 904919 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6560. Min Act: -0.0000

Data Index: 121777 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6705. Min Act: 0.0000

Data Index: 506313 (The Pile)

Max Activating Token Index: 70