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

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

Neuron 954 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: 0.5153. Min Range: -0.5153

Max Act: 0.4770. Min Act: -0.0004

Data Index: 1552128 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4920. Min Act: -0.0004

Data Index: 1495882 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4358. Min Act: -0.0004

Data Index: 1653932 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4475. Min Act: -0.0004

Data Index: 1380055 (Python Code)

Max Activating Token Index: 737

Text #4

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3886. Min Act: -0.0004

Data Index: 1640328 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4430. Min Act: -0.0004

Data Index: 1509333 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.5153. Min Act: -0.0004

Data Index: 777691 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4855. Min Act: -0.0004

Data Index: 880572 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4466. Min Act: -0.0004

Data Index: 1465380 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4098. Min Act: -0.0004

Data Index: 745237 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4359. Min Act: -0.0004

Data Index: 1260623 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4365. Min Act: -0.0004

Data Index: 1650685 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4349. Min Act: -0.0004

Data Index: 1487250 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3670. Min Act: -0.0004

Data Index: 855347 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3740. Min Act: -0.0004

Data Index: 867277 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3628. Min Act: -0.0004

Data Index: 62100 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3993. Min Act: -0.0004

Data Index: 1071664 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4404. Min Act: -0.0004

Data Index: 120182 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4377. Min Act: -0.0004

Data Index: 373970 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3564. Min Act: -0.0004

Data Index: 1076039 (C4 (Web Text))

Max Activating Token Index: 400