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

Dataset: The Pile

Neuron 4789 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: 1.7186. Min Range: -1.7186

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1008396 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.5240. Min Act: -0.0000

Data Index: 692545 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.7186. Min Act: -0.0000

Data Index: 78243 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1031663 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1206328 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1308427 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.4493. Min Act: -0.0000

Data Index: 1751819 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1367140 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.5366. Min Act: -0.0000

Data Index: 821159 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1773340 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1350055 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.4163. Min Act: -0.0000

Data Index: 978721 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1783779 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2263. Min Act: -0.0000

Data Index: 150053 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.3705. Min Act: -0.0000

Data Index: 645534 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1388418 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2815. Min Act: -0.0000

Data Index: 52989 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.2595. Min Act: -0.0000

Data Index: 671302 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 1.7186. Min Range: -1.7186

Max Act: 0.9540. Min Act: -0.0000

Data Index: 930949 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1504436 (The Pile)

Max Activating Token Index: 403