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

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

Neuron 3225 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: 0.9152. Min Range: -0.9152

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1356390 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.8152. Min Act: -0.0001

Data Index: 251700 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7927. Min Act: -0.0001

Data Index: 60694 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7818. Min Act: -0.0000

Data Index: 939152 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.8060. Min Act: -0.0001

Data Index: 390998 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1217024 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7230. Min Act: -0.0000

Data Index: 156378 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7371. Min Act: -0.0001

Data Index: 238507 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7100. Min Act: -0.0001

Data Index: 498228 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1256747 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1049322 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7226. Min Act: -0.0001

Data Index: 578466 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7211. Min Act: -0.0001

Data Index: 176623 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7128. Min Act: -0.0000

Data Index: 188527 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1054000 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1328639 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6895. Min Act: -0.0000

Data Index: 191296 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6663. Min Act: -0.0001

Data Index: 633371 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6876. Min Act: -0.0001

Data Index: 730123 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1118912 (C4 (Web Text))

Max Activating Token Index: 77