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

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

Neuron 904 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: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1252033 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0183. Min Act: -0.0005

Data Index: 956698 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1423250 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0172. Min Act: -0.0005

Data Index: 771753 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0167. Min Act: -0.0005

Data Index: 603487 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1210801 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1155974 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1470503 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0166. Min Act: -0.0005

Data Index: 325452 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1584113 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0166. Min Act: -0.0006

Data Index: 138064 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1132908 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1544135 (Python Code)

Max Activating Token Index: 670

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1600046 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1533839 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1587603 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0153. Min Act: -0.0005

Data Index: 890165 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1425343 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0147. Min Act: -0.0005

Data Index: 1010540 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1622230 (Python Code)

Max Activating Token Index: 654