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

Dataset: The Pile

Neuron 504 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: 1.1157. Min Range: -1.1157

Max Act: 1.0918. Min Act: -0.0000

Data Index: 711431 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 1.1157. Min Range: -1.1157

Max Act: 1.1157. Min Act: -0.0000

Data Index: 518719 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9948. Min Act: -0.0000

Data Index: 849624 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1393976 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1693336 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8762. Min Act: -0.0000

Data Index: 105829 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1449126 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1993307 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8159. Min Act: -0.0000

Data Index: 504476 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1950447 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7912. Min Act: -0.0000

Data Index: 507018 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1404743 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7887. Min Act: -0.0000

Data Index: 196639 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7405. Min Act: -0.0000

Data Index: 338629 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7575. Min Act: -0.0000

Data Index: 904016 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1123773 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7152. Min Act: -0.0000

Data Index: 844053 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6950. Min Act: -0.0000

Data Index: 906613 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7512. Min Act: -0.0000

Data Index: 393148 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1075658 (The Pile)

Max Activating Token Index: 111