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

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

Neuron 1901 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3442. Min Act: -0.0002

Data Index: 1556852 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3454. Min Act: -0.0002

Data Index: 1522769 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3336. Min Act: -0.0002

Data Index: 370064 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3273. Min Act: -0.0002

Data Index: 507651 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3243. Min Act: -0.0002

Data Index: 1041727 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3179. Min Act: -0.0002

Data Index: 526539 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3177. Min Act: -0.0002

Data Index: 1183097 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3129. Min Act: -0.0002

Data Index: 370989 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3170. Min Act: -0.0002

Data Index: 266629 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3178. Min Act: -0.0002

Data Index: 915184 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3114. Min Act: -0.0002

Data Index: 451404 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3063. Min Act: -0.0002

Data Index: 1465558 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3136. Min Act: -0.0002

Data Index: 362187 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3017. Min Act: -0.0003

Data Index: 134843 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3054. Min Act: -0.0002

Data Index: 1471684 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3057. Min Act: -0.0002

Data Index: 1362985 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2982. Min Act: -0.0002

Data Index: 446803 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3025. Min Act: -0.0002

Data Index: 1221382 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3073. Min Act: -0.0002

Data Index: 1122231 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2997. Min Act: -0.0002

Data Index: 1654886 (Python Code)

Max Activating Token Index: 224