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

Dataset: The Pile

Neuron 4071 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: 5.4377. Min Range: -5.4377

Max Act: 5.4377. Min Act: -0.0000

Data Index: 402346 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.3194. Min Act: -0.0000

Data Index: 1605991 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.1099. Min Act: -0.0000

Data Index: 113941 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.0782. Min Act: -0.0000

Data Index: 116724 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.0854. Min Act: -0.0000

Data Index: 185736 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.0757. Min Act: -0.0000

Data Index: 268030 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 5.4377. Min Range: -5.4377

Max Act: 5.0281. Min Act: -0.0000

Data Index: 1618454 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.8172. Min Act: -0.0000

Data Index: 1306509 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7893. Min Act: -0.0000

Data Index: 1646727 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7654. Min Act: -0.0000

Data Index: 777501 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7736. Min Act: -0.0000

Data Index: 93072 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.5666. Min Act: -0.0000

Data Index: 1399586 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.5660. Min Act: -0.0000

Data Index: 969581 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.9261. Min Act: -0.0000

Data Index: 1158206 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7031. Min Act: -0.0000

Data Index: 1218492 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.6779. Min Act: -0.0000

Data Index: 909849 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.6688. Min Act: -0.0000

Data Index: 56171 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.6553. Min Act: -0.0000

Data Index: 1534060 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.6373. Min Act: -0.0000

Data Index: 1967351 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.4383. Min Act: -0.0000

Data Index: 1082048 (The Pile)

Max Activating Token Index: 857