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

Dataset: The Pile

Neuron 3652 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1223671 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.5673. Min Act: -0.0000

Data Index: 931466 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1653866 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1120058 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1214027 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.1413. Min Act: -0.0000

Data Index: 270703 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.0756. Min Act: -0.0000

Data Index: 566338 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1414350 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.0000. Min Act: -0.0000

Data Index: 898991 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1037643 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.5673. Min Range: -1.5673

Max Act: 1.1094. Min Act: -0.0000

Data Index: 283845 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1215818 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1141969 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9489. Min Act: -0.0000

Data Index: 586662 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9317. Min Act: -0.0000

Data Index: 931410 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9410. Min Act: -0.0000

Data Index: 124033 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.8784. Min Act: -0.0000

Data Index: 366685 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1485128 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1421126 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.5673. Min Range: -1.5673

Max Act: 0.8481. Min Act: -0.0000

Data Index: 913128 (The Pile)

Max Activating Token Index: 348