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

Dataset: The Pile

Neuron 3821 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: 1.5154. Min Range: -1.5154

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1397120 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1951254 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2828. Min Act: -0.0000

Data Index: 696285 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3361. Min Act: -0.0000

Data Index: 567565 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1162889 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1489121 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1557. Min Act: -0.0000

Data Index: 829507 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1519802 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2123. Min Act: -0.0000

Data Index: 894977 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1693030 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1255073 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1044985 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2288. Min Act: -0.0000

Data Index: 114941 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1016. Min Act: -0.0000

Data Index: 479367 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1973990 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1334. Min Act: -0.0000

Data Index: 798634 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1789893 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0895. Min Act: -0.0000

Data Index: 49633 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1873. Min Act: -0.0000

Data Index: 796668 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0788. Min Act: -0.0000

Data Index: 305269 (The Pile)

Max Activating Token Index: 604