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

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

Neuron 1281 in Layer 0

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: 0.0220. Min Range: -0.0220

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1291814 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1018985 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0178. Min Act: -0.0001

Data Index: 854203 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1252681 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0168. Min Act: -0.0001

Data Index: 335688 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0160. Min Act: -0.0001

Data Index: 212403 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0161. Min Act: -0.0001

Data Index: 78049 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0156. Min Act: -0.0001

Data Index: 552210 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1195328 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1423085 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0155. Min Act: -0.0001

Data Index: 9599 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0152. Min Act: -0.0001

Data Index: 785166 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1569583 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0150. Min Act: -0.0001

Data Index: 87021 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0149. Min Act: -0.0001

Data Index: 157162 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1512381 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1429649 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1651270 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1289684 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1450095 (Python Code)

Max Activating Token Index: 26