Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2116 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.9446. Min Act: -0.0004

Data Index: 472640 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.9117. Min Act: -0.0004

Data Index: 1068996 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8132. Min Act: -0.0004

Data Index: 1333524 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8060. Min Act: -0.0004

Data Index: 356772 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8738. Min Act: -0.0004

Data Index: 809675 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8691. Min Act: -0.0004

Data Index: 604607 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8115. Min Act: -0.0004

Data Index: 1188514 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7315. Min Act: -0.0004

Data Index: 163555 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7501. Min Act: -0.0004

Data Index: 503080 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7954. Min Act: -0.0004

Data Index: 337296 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7704. Min Act: -0.0004

Data Index: 432339 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7380. Min Act: -0.0004

Data Index: 1287243 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7122. Min Act: -0.0004

Data Index: 348576 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7288. Min Act: -0.0004

Data Index: 86150 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7090. Min Act: -0.0004

Data Index: 662624 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7267. Min Act: -0.0004

Data Index: 777851 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7772. Min Act: -0.0004

Data Index: 667226 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7725. Min Act: -0.0004

Data Index: 243684 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7233. Min Act: -0.0004

Data Index: 464462 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6319. Min Act: -0.0004

Data Index: 1052849 (C4 (Web Text))

Max Activating Token Index: 377