Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1575 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1636611 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1619102 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1412729 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1580914 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1489215 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1443646 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1588745 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1481840 (Python Code)

Max Activating Token Index: 282

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0006

Data Index: 227615 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1588253 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1180212 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1650701 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1488309 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0141. Min Act: -0.0006

Data Index: 505549 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1535437 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1613837 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1468590 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1345187 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0143. Min Act: -0.0006

Data Index: 33521 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1642042 (Python Code)

Max Activating Token Index: 460