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

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

Neuron 740 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.3433. Min Act: -0.0001

Data Index: 595452 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.3112. Min Act: -0.0001

Data Index: 518361 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0815. Min Act: -0.0001

Data Index: 1245322 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9843. Min Act: -0.0001

Data Index: 30011 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9757. Min Act: -0.0001

Data Index: 477787 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9436. Min Act: -0.0001

Data Index: 195474 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9279. Min Act: -0.0001

Data Index: 38543 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9274. Min Act: -0.0001

Data Index: 256861 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9296. Min Act: -0.0001

Data Index: 848138 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9165. Min Act: -0.0001

Data Index: 205180 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8397. Min Act: -0.0001

Data Index: 800195 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0898. Min Act: -0.0001

Data Index: 179229 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1037466 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8615. Min Act: -0.0001

Data Index: 1019957 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8458. Min Act: -0.0001

Data Index: 945830 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8918. Min Act: -0.0001

Data Index: 1151966 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9072. Min Act: -0.0001

Data Index: 23769 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9121. Min Act: -0.0001

Data Index: 140421 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9076. Min Act: -0.0001

Data Index: 405352 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9078. Min Act: -0.0001

Data Index: 96045 (C4 (Web Text))

Max Activating Token Index: 552