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

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

Neuron 5158 in Layer 1

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: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1276599 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1573799 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1545994 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1514757 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0002

Data Index: 412712 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0002

Data Index: 931834 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1339614 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1651024 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1637890 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1638671 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1434924 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1568872 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1622074 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0145. Min Act: -0.0002

Data Index: 72713 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0144. Min Act: -0.0002

Data Index: 322742 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1617502 (Python Code)

Max Activating Token Index: 103

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1564379 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1274402 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1583239 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1363176 (Python Code)

Max Activating Token Index: 704