Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3037 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 97799 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1494908 (Python Code)

Max Activating Token Index: 229

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1549312 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1580961 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1488716 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1226584 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0002

Data Index: 968600 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1176553 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0002

Data Index: 595065 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1433683 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0002

Data Index: 659860 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1192653 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1609476 (Python Code)

Max Activating Token Index: 277

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1404639 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1419556 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0002

Data Index: 219914 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1543390 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0002

Data Index: 391967 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0132. Min Act: -0.0002

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0129. Min Act: -0.0002

Data Index: 879688 (C4 (Web Text))

Max Activating Token Index: 146