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

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

Neuron 945 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1408421 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1136403 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1606869 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1574404 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1469368 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1190359 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1082666 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1400669 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1411607 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1480958 (Python Code)

Max Activating Token Index: 1008

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1490205 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1378896 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1490150 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0153. Min Act: -0.0003

Data Index: 166312 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1302922 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0147. Min Act: -0.0003

Data Index: 929966 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1301020 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1572435 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1553957 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0138. Min Act: -0.0003

Data Index: 276433 (C4 (Web Text))

Max Activating Token Index: 28