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

Dataset: The Pile

Neuron 2659 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: 0.5811. Min Range: -0.5811

Max Act: 0.5811. Min Act: -0.0000

Data Index: 268217 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1065287 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3951. Min Act: -0.0000

Data Index: 332680 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3912. Min Act: -0.0000

Data Index: 399928 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1993231 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4037. Min Act: -0.0000

Data Index: 440525 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3726. Min Act: -0.0000

Data Index: 24855 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1291668 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1289713 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4088. Min Act: -0.0000

Data Index: 597655 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4055. Min Act: -0.0000

Data Index: 328555 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3747. Min Act: -0.0000

Data Index: 298362 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1705608 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3178. Min Act: -0.0000

Data Index: 464676 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3080. Min Act: -0.0000

Data Index: 506502 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1928251 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3114. Min Act: -0.0000

Data Index: 902942 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1682629 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1146906 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3216. Min Act: -0.0000

Data Index: 666444 (The Pile)

Max Activating Token Index: 61