Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1777 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0001

Data Index: 529206 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1072150 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1496439 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0158. Min Act: -0.0001

Data Index: 230109 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0001

Data Index: 53850 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0001

Data Index: 706519 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1425741 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1255715 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1078135 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0001

Data Index: 433137 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0001

Data Index: 59991 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1501997 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0001

Data Index: 86501 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1587470 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1093654 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1189195 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0001

Data Index: 829957 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0001

Data Index: 725073 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1424024 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1379082 (Python Code)

Max Activating Token Index: 23