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

Dataset: The Pile

Neuron 4713 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: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 775410 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4572. Min Act: -0.0000

Data Index: 301478 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4725. Min Act: -0.0000

Data Index: 177227 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1407691 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1382317 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4521. Min Act: -0.0000

Data Index: 505009 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1160184 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1215437 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1501432 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4083. Min Act: -0.0000

Data Index: 73771 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1560048 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1985096 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1604246 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3875. Min Act: -0.0000

Data Index: 321304 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3372. Min Act: -0.0000

Data Index: 317892 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3718. Min Act: -0.0000

Data Index: 909916 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1119952 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3865. Min Act: -0.0000

Data Index: 243264 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3751. Min Act: -0.0000

Data Index: 782773 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4016. Min Act: -0.0000

Data Index: 963260 (The Pile)

Max Activating Token Index: 429