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

Dataset: The Pile

Neuron 145 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: 0.6819. Min Range: -0.6819

Max Act: 0.6819. Min Act: -0.0000

Data Index: 976868 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6297. Min Act: -0.0000

Data Index: 664188 (The Pile)

Max Activating Token Index: 50

Text #2

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6452. Min Act: -0.0000

Data Index: 669896 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6240. Min Act: -0.0000

Data Index: 743598 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6238. Min Act: -0.0000

Data Index: 270015 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5966. Min Act: -0.0000

Data Index: 805060 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1350466 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1547235 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1630528 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1537422 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1066451 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1144038 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1505611 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1445760 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5637. Min Act: -0.0000

Data Index: 944422 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1930001 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1235325 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5847. Min Act: -0.0000

Data Index: 494318 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1109386 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.6819. Min Range: -0.6819

Max Act: 0.5950. Min Act: -0.0000

Data Index: 159058 (The Pile)

Max Activating Token Index: 677