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

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

Neuron 6047 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2395. Min Range: -8.2395

Max Act: 8.2395. Min Act: -0.0000

Data Index: 568151 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 8.2395. Min Range: -8.2395

Max Act: 7.5966. Min Act: -0.0000

Data Index: 816516 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 8.2395. Min Range: -8.2395

Max Act: 7.7197. Min Act: -0.0000

Data Index: 16696 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.8118. Min Act: -0.0000

Data Index: 1130086 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 8.2395. Min Range: -8.2395

Max Act: 7.6253. Min Act: -0.0000

Data Index: 299122 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.9880. Min Act: -0.0000

Data Index: 1165233 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 8.2395. Min Range: -8.2395

Max Act: 7.2440. Min Act: -0.0001

Data Index: 1350065 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.8180. Min Act: -0.0000

Data Index: 893370 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.7599. Min Act: -0.0000

Data Index: 653698 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.9520. Min Act: -0.0000

Data Index: 568755 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.7367. Min Act: -0.0000

Data Index: 939962 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.5581. Min Act: -0.0000

Data Index: 1168260 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.8618. Min Act: -0.0000

Data Index: 166327 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.8034. Min Act: -0.0001

Data Index: 991101 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.9255. Min Act: -0.0000

Data Index: 6618 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.9805. Min Act: -0.0000

Data Index: 294472 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.6344. Min Act: -0.0001

Data Index: 989143 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.2187. Min Act: -0.0000

Data Index: 746828 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.5288. Min Act: -0.0000

Data Index: 388364 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 8.2395. Min Range: -8.2395

Max Act: 6.9440. Min Act: -0.0000

Data Index: 53676 (C4 (Web Text))

Max Activating Token Index: 264