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

Dataset: The Pile

Neuron 2815 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: 1.6659. Min Range: -1.6659

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1601589 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.6517. Min Act: -0.0000

Data Index: 915876 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1091455 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5584. Min Act: -0.0000

Data Index: 209024 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5356. Min Act: -0.0000

Data Index: 806768 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1882157 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4194. Min Act: -0.0000

Data Index: 837048 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4501. Min Act: -0.0000

Data Index: 840636 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5194. Min Act: -0.0000

Data Index: 351223 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4798. Min Act: -0.0000

Data Index: 970462 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1670062 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5138. Min Act: -0.0000

Data Index: 1574536 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1559217 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1550351 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1716478 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4136. Min Act: -0.0000

Data Index: 338664 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4529. Min Act: -0.0000

Data Index: 239672 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1859886 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5280. Min Act: -0.0000

Data Index: 543483 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1720442 (The Pile)

Max Activating Token Index: 1018