Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.5647. Min Act: -0.0000

Data Index: 531335 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.6301. Min Act: -0.0000

Data Index: 788262 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.7019. Min Act: -0.0000

Data Index: 588864 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.5381. Min Act: -0.0000

Data Index: 618837 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.4678. Min Act: -0.0000

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.4339. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.4162. Min Act: -0.0000

Data Index: 578299 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.4867. Min Act: -0.0000

Data Index: 193721 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.3620. Min Act: -0.0000

Data Index: 93481 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1329415 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.4165. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.3035. Min Act: -0.0000

Data Index: 680120 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2380. Min Act: -0.0000

Data Index: 554266 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2121. Min Act: -0.0000

Data Index: 335618 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2161. Min Act: -0.0000

Data Index: 53313 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2817. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1132. Min Act: -0.0000

Data Index: 581223 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1058441 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1009027 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2246. Min Act: -0.0000

Data Index: 273744 (C4 (Web Text))

Max Activating Token Index: 562