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

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

Neuron 292 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: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1329851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0225. Min Act: -0.0006

Data Index: 542046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0187. Min Act: -0.0006

Data Index: 99187 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0178. Min Act: -0.0006

Data Index: 811480 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1442269 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0144. Min Act: -0.0006

Data Index: 687015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0135. Min Act: -0.0006

Data Index: 765209 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1484640 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0162. Min Act: -0.0006

Data Index: 971382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1536384 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0135. Min Act: -0.0006

Data Index: 854531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0182. Min Act: -0.0006

Data Index: 431342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1628374 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0161. Min Act: -0.0006

Data Index: 843493 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0126. Min Act: -0.0006

Data Index: 66729 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0164. Min Act: -0.0006

Data Index: 819085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1282989 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1594496 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0149. Min Act: -0.0006

Data Index: 440112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1443285 (Python Code)

Max Activating Token Index: 1023