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

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

Neuron 4643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1114871 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1158284 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1169875 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1330046 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1109142 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4398. Min Act: -0.0000

Data Index: 465209 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4913. Min Act: -0.0000

Data Index: 19718 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4350. Min Act: -0.0000

Data Index: 739354 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1338401 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3464. Min Act: -0.0000

Data Index: 524780 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3575. Min Act: -0.0000

Data Index: 748024 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3278. Min Act: -0.0000

Data Index: 975874 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3864. Min Act: -0.0000

Data Index: 715079 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3381. Min Act: -0.0000

Data Index: 96132 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3221. Min Act: -0.0000

Data Index: 450421 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3229. Min Act: -0.0000

Data Index: 786626 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3129. Min Act: -0.0000

Data Index: 111311 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3083. Min Act: -0.0000

Data Index: 716025 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.2928. Min Act: -0.0000

Data Index: 553382 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1338609 (C4 (Web Text))

Max Activating Token Index: 889