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

Dataset: The Pile

Neuron 3761 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: 1.1570. Min Range: -1.1570

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1961680 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0969. Min Act: -0.0000

Data Index: 803133 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0176. Min Act: -0.0000

Data Index: 932628 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1116170 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1169141 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0169. Min Act: -0.0000

Data Index: 732655 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.1135. Min Act: -0.0000

Data Index: 418227 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1920809 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0213. Min Act: -0.0000

Data Index: 958552 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1091655 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9451. Min Act: -0.0000

Data Index: 510975 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9503. Min Act: -0.0000

Data Index: 461255 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1653493 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9736. Min Act: -0.0000

Data Index: 934090 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.1570. Min Range: -1.1570

Max Act: 1.0039. Min Act: -0.0000

Data Index: 920561 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1876081 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9806. Min Act: -0.0000

Data Index: 145348 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1909226 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9939. Min Act: -0.0000

Data Index: 650378 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.1570. Min Range: -1.1570

Max Act: 0.9031. Min Act: -0.0000

Data Index: 311221 (The Pile)

Max Activating Token Index: 462