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

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

Neuron 283 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1539312 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1526170 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1569563 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1409668 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1390276 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1496029 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1442608 (Python Code)

Max Activating Token Index: 720

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1589615 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1529598 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1423984 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1060456 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1382227 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1409053 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1529878 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1382109 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1404263 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1364988 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1164518 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1534593 (Python Code)

Max Activating Token Index: 528

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0002

Data Index: 447474 (C4 (Web Text))

Max Activating Token Index: 378