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

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

Neuron 3082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1133110 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.5903. Min Act: -0.0000

Data Index: 943759 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.3822. Min Act: -0.0000

Data Index: 340612 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.3417. Min Act: -0.0001

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.3364. Min Act: -0.0001

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.3206. Min Act: -0.0001

Data Index: 357801 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2779. Min Act: -0.0001

Data Index: 13915 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1031171 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2527. Min Act: -0.0001

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2389. Min Act: -0.0001

Data Index: 675291 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2357. Min Act: -0.0001

Data Index: 438323 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1818. Min Act: -0.0001

Data Index: 225338 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2101. Min Act: -0.0000

Data Index: 221344 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1748. Min Act: -0.0001

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2022. Min Act: -0.0001

Data Index: 738067 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1352. Min Act: -0.0001

Data Index: 1186185 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1696. Min Act: -0.0001

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1154. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1111. Min Act: -0.0001

Data Index: 118122 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1026. Min Act: -0.0001

Data Index: 972437 (C4 (Web Text))

Max Activating Token Index: 40