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

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

Neuron 1400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.6505. Min Act: -0.0001

Data Index: 936744 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.7357. Min Act: -0.0001

Data Index: 398343 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.6744. Min Act: -0.0001

Data Index: 233885 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5805. Min Act: -0.0001

Data Index: 536159 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.6503. Min Act: -0.0001

Data Index: 566849 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5447. Min Act: -0.0001

Data Index: 294473 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5076. Min Act: -0.0001

Data Index: 1246844 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5389. Min Act: -0.0001

Data Index: 595365 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.6730. Min Act: -0.0001

Data Index: 1302329 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5457. Min Act: -0.0001

Data Index: 1289132 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.6258. Min Act: -0.0001

Data Index: 17532 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4778. Min Act: -0.0001

Data Index: 384936 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4994. Min Act: -0.0001

Data Index: 1201441 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3698. Min Act: -0.0001

Data Index: 1120961 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4217. Min Act: -0.0001

Data Index: 648139 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4972. Min Act: -0.0001

Data Index: 969646 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3694. Min Act: -0.0001

Data Index: 704464 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5322. Min Act: -0.0001

Data Index: 912242 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4049. Min Act: -0.0001

Data Index: 17296 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3261. Min Act: -0.0001

Data Index: 1057288 (C4 (Web Text))

Max Activating Token Index: 808