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

Dataset: The Pile

Neuron 2443 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: 0.2763. Min Range: -0.2763

Max Act: 0.2763. Min Act: -0.0000

Data Index: 577 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1202954 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1834938 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1325589 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1942719 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2373. Min Act: -0.0000

Data Index: 981016 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2379. Min Act: -0.0000

Data Index: 938522 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2105. Min Act: -0.0000

Data Index: 291531 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1679221 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2190. Min Act: -0.0000

Data Index: 496766 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1028425 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2100. Min Act: -0.0000

Data Index: 522201 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1065082 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1478514 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2177. Min Act: -0.0000

Data Index: 335619 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2043. Min Act: -0.0000

Data Index: 572441 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1402094 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1269045 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1235598 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2075. Min Act: -0.0000

Data Index: 333828 (The Pile)

Max Activating Token Index: 365