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

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

Neuron 978 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: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0002

Data Index: 518487 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1227034 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0171. Min Act: -0.0002

Data Index: 347722 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0175. Min Act: -0.0002

Data Index: 789606 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1270283 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0153. Min Act: -0.0002

Data Index: 167143 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0165. Min Act: -0.0002

Data Index: 937694 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1257984 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0163. Min Act: -0.0002

Data Index: 984070 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0149. Min Act: -0.0002

Data Index: 417558 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1256916 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0142. Min Act: -0.0002

Data Index: 328733 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0140. Min Act: -0.0002

Data Index: 640265 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1150568 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0142. Min Act: -0.0002

Data Index: 190331 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0148. Min Act: -0.0002

Data Index: 118913 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0136. Min Act: -0.0002

Data Index: 215176 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1210742 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0138. Min Act: -0.0001

Data Index: 979795 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0143. Min Act: -0.0002

Data Index: 120363 (C4 (Web Text))

Max Activating Token Index: 264