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

Dataset: The Pile

Neuron 2712 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: 0.8476. Min Range: -0.8476

Max Act: 0.8476. Min Act: 0.0000

Data Index: 240783 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.8057. Min Act: 0.0000

Data Index: 824129 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7585. Min Act: -0.0000

Data Index: 873390 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1783365 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1345897 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1472783 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6653. Min Act: -0.0000

Data Index: 83557 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1531721 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1251136 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1972928 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1027665 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1567609 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5121. Min Act: -0.0000

Data Index: 116683 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1692149 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.4784. Min Act: -0.0000

Data Index: 479289 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1022128 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.4981. Min Act: -0.0000

Data Index: 895566 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5190. Min Act: -0.0000

Data Index: 237170 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5155. Min Act: -0.0000

Data Index: 280757 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5174. Min Act: -0.0000

Data Index: 278401 (The Pile)

Max Activating Token Index: 447