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

Dataset: The Pile

Neuron 1243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0000

Data Index: 838436 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1911389 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1401930 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1929950 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8002. Min Act: -0.0000

Data Index: 48175 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7611. Min Act: -0.0000

Data Index: 536625 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7899. Min Act: -0.0000

Data Index: 423654 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7466. Min Act: -0.0000

Data Index: 221181 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7913. Min Act: -0.0000

Data Index: 427466 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1913422 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1344163 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7283. Min Act: -0.0000

Data Index: 83010 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1663195 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7527. Min Act: -0.0000

Data Index: 684179 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7820. Min Act: -0.0000

Data Index: 796802 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7225. Min Act: -0.0000

Data Index: 168032 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1386232 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1855029 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7095. Min Act: -0.0000

Data Index: 651333 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1904504 (The Pile)

Max Activating Token Index: 318