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

Dataset: The Pile

Neuron 3501 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: 3.4266. Min Range: -3.4266

Max Act: 3.4266. Min Act: -0.0000

Data Index: 564992 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.8673. Min Act: -0.0000

Data Index: 1140664 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.8212. Min Act: -0.0000

Data Index: 576229 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1089435 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1680802 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1318969 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3716. Min Act: -0.0000

Data Index: 387425 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3703. Min Act: -0.0000

Data Index: 983753 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3144. Min Act: -0.0000

Data Index: 76173 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1872904 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1864363 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1753100 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2432. Min Act: -0.0000

Data Index: 107632 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1107732 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1413303 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2393. Min Act: -0.0000

Data Index: 596600 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.0776. Min Act: -0.0000

Data Index: 733782 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2155. Min Act: -0.0000

Data Index: 808961 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.1355. Min Act: -0.0000

Data Index: 275635 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 3.4266. Min Range: -3.4266

Max Act: 1.2680. Min Act: -0.0000

Data Index: 962668 (The Pile)

Max Activating Token Index: 92