Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0004

Data Index: 881359 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1587407 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1029588 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0004

Data Index: 778601 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0177. Min Act: -0.0004

Data Index: 1595696 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0157. Min Act: -0.0004

Data Index: 403028 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0161. Min Act: -0.0004

Data Index: 1489860 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0166. Min Act: -0.0004

Data Index: 1565604 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1462039 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0155. Min Act: -0.0004

Data Index: 243538 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0151. Min Act: -0.0004

Data Index: 686387 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1584120 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1462249 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0140. Min Act: -0.0004

Data Index: 194744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1632648 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0146. Min Act: -0.0004

Data Index: 273698 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0142. Min Act: -0.0004

Data Index: 623928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0145. Min Act: -0.0004

Data Index: 587964 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0146. Min Act: -0.0004

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 873