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

Dataset: The Pile

Neuron 3458 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: 1.1246. Min Range: -1.1246

Max Act: 1.1246. Min Act: -0.0000

Data Index: 148750 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 1.1246. Min Range: -1.1246

Max Act: 1.0146. Min Act: -0.0000

Data Index: 809617 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.1246. Min Range: -1.1246

Max Act: 1.0311. Min Act: -0.0000

Data Index: 934063 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 1.1246. Min Range: -1.1246

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1529133 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 1.1246. Min Range: -1.1246

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1342314 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9239. Min Act: -0.0000

Data Index: 309304 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9848. Min Act: -0.0000

Data Index: 782431 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9097. Min Act: -0.0000

Data Index: 233026 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1454165 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9509. Min Act: -0.0000

Data Index: 741756 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.1246. Min Range: -1.1246

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1634903 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1959885 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1019549 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9540. Min Act: -0.0000

Data Index: 997760 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9573. Min Act: -0.0000

Data Index: 761648 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1049081 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1600408 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.8938. Min Act: -0.0001

Data Index: 1796614 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1044645 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.1246. Min Range: -1.1246

Max Act: 0.9292. Min Act: -0.0000

Data Index: 36354 (The Pile)

Max Activating Token Index: 326