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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3138. Min Range: -2.3138

Max Act: 2.3138. Min Act: -0.0000

Data Index: 1181271 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.3138. Min Range: -2.3138

Max Act: 2.1711. Min Act: -0.0000

Data Index: 70807 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.3138. Min Range: -2.3138

Max Act: 2.2101. Min Act: -0.0000

Data Index: 1284995 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 2.3138. Min Range: -2.3138

Max Act: 2.0207. Min Act: -0.0000

Data Index: 710011 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9948. Min Act: -0.0000

Data Index: 536499 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9869. Min Act: -0.0000

Data Index: 936106 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.8638. Min Act: -0.0000

Data Index: 719195 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.8417. Min Act: -0.0000

Data Index: 703736 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9393. Min Act: -0.0000

Data Index: 946662 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9320. Min Act: -0.0000

Data Index: 655307 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9113. Min Act: -0.0000

Data Index: 379934 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.8740. Min Act: -0.0000

Data Index: 912045 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.8411. Min Act: -0.0000

Data Index: 401063 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9517. Min Act: -0.0000

Data Index: 708885 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1318559 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.9012. Min Act: -0.0000

Data Index: 426788 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.6913. Min Act: -0.0000

Data Index: 981051 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.7587. Min Act: -0.0000

Data Index: 477631 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.7625. Min Act: -0.0000

Data Index: 518246 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.3138. Min Range: -2.3138

Max Act: 1.7121. Min Act: -0.0000

Data Index: 730845 (C4 (Web Text))

Max Activating Token Index: 710