Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3054 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.3254. Min Act: -0.0000

Data Index: 200962 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.6908. Min Act: -0.0000

Data Index: 701557 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.5882. Min Act: -0.0000

Data Index: 38830 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.7495. Min Act: -0.0000

Data Index: 1529720 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.0715. Min Act: -0.0000

Data Index: 1230626 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.4228. Min Act: -0.0000

Data Index: 506794 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.4203. Min Act: -0.0000

Data Index: 917411 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.3927. Min Act: -0.0000

Data Index: 1628229 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.8866. Min Act: -0.0000

Data Index: 1380115 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.1600. Min Act: -0.0000

Data Index: 850481 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.6946. Min Act: -0.0000

Data Index: 59055 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1306500 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.5182. Min Act: -0.0000

Data Index: 333005 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.2277. Min Act: -0.0000

Data Index: 1934520 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.9005. Min Act: -0.0000

Data Index: 345825 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.4472. Min Act: -0.0000

Data Index: 1846361 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.5747. Min Act: -0.0000

Data Index: 1191523 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.4167. Min Act: -0.0000

Data Index: 1123495 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.6944. Min Act: -0.0000

Data Index: 989617 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.9566. Min Act: -0.0000

Data Index: 1967503 (The Pile)

Max Activating Token Index: 656