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

Dataset: The Pile

Neuron 3910 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: 1.4591. Min Range: -1.4591

Max Act: 1.4591. Min Act: -0.0000

Data Index: 476455 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.3648. Min Act: -0.0000

Data Index: 808039 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1704070 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.3180. Min Act: -0.0000

Data Index: 653002 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.1965. Min Act: -0.0000

Data Index: 309513 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1653812 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1665467 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0470. Min Act: -0.0000

Data Index: 306874 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0343. Min Act: -0.0000

Data Index: 938681 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9857. Min Act: -0.0000

Data Index: 905139 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1895260 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1496595 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9660. Min Act: -0.0000

Data Index: 87653 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1410192 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1309826 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9265. Min Act: -0.0000

Data Index: 622145 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8934. Min Act: -0.0000

Data Index: 552624 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8228. Min Act: -0.0000

Data Index: 867438 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1031589 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8615. Min Act: -0.0000

Data Index: 690005 (The Pile)

Max Activating Token Index: 485