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

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

Neuron 1945 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1646259 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1621511 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1055013 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1461921 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3809. Min Act: -0.0000

Data Index: 397262 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1491597 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3431. Min Act: -0.0000

Data Index: 627632 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1463062 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3107. Min Act: -0.0000

Data Index: 418239 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1494894 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1652702 (Python Code)

Max Activating Token Index: 193

Text #11

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1488930 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3131. Min Act: -0.0000

Data Index: 108339 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1542559 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3292. Min Act: -0.0000

Data Index: 43836 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1612397 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1267945 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1057340 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1584100 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 0.5441. Min Range: -0.5441

Max Act: 0.2789. Min Act: -0.0000

Data Index: 406221 (C4 (Web Text))

Max Activating Token Index: 99