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

Dataset: The Pile

Neuron 3723 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: 0.7149. Min Range: -0.7149

Max Act: 0.7149. Min Act: -0.0000

Data Index: 818001 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.7063. Min Act: -0.0000

Data Index: 382222 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1851852 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.6667. Min Act: -0.0000

Data Index: 386892 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5786. Min Act: -0.0000

Data Index: 763523 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.6039. Min Act: -0.0000

Data Index: 830801 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1931174 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5802. Min Act: -0.0000

Data Index: 841170 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5762. Min Act: -0.0000

Data Index: 865490 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1453954 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4982. Min Act: -0.0000

Data Index: 10205 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1061253 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5301. Min Act: -0.0000

Data Index: 944723 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5270. Min Act: -0.0000

Data Index: 538850 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5464. Min Act: -0.0000

Data Index: 669166 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5069. Min Act: -0.0000

Data Index: 482723 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5134. Min Act: -0.0000

Data Index: 572479 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1155879 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5452. Min Act: -0.0000

Data Index: 85378 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4815. Min Act: -0.0000

Data Index: 727157 (The Pile)

Max Activating Token Index: 182