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

Dataset: The Pile

Neuron 2346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.0000

Data Index: 55238 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.0470. Min Act: -0.0000

Data Index: 809764 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.7035. Min Act: -0.0000

Data Index: 1608588 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.8263. Min Act: -0.0000

Data Index: 656900 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.9829. Min Act: -0.0000

Data Index: 136077 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.7098. Min Act: -0.0000

Data Index: 1531527 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.7427. Min Act: -0.0000

Data Index: 237241 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.8690. Min Act: -0.0000

Data Index: 101298 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.5752. Min Act: -0.0000

Data Index: 549642 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.8099. Min Act: -0.0000

Data Index: 786527 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.7864. Min Act: -0.0000

Data Index: 611516 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.6156. Min Act: -0.0000

Data Index: 811841 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.5310. Min Act: -0.0000

Data Index: 1599377 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.6015. Min Act: -0.0000

Data Index: 1468228 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1125109 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.5921. Min Act: -0.0000

Data Index: 398623 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.5598. Min Act: -0.0000

Data Index: 1709089 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.4042. Min Act: -0.0000

Data Index: 951908 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.4916. Min Act: -0.0000

Data Index: 1672550 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 3.2253. Min Range: -3.2253

Max Act: 2.2335. Min Act: -0.0000

Data Index: 947204 (The Pile)

Max Activating Token Index: 186