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

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

Neuron 1904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1455688 (Python Code)

Max Activating Token Index: 745

Text #1

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1642040 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1308640 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1468070 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1150. Min Act: -0.0000

Data Index: 436880 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1112. Min Act: -0.0000

Data Index: 23683 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1158. Min Act: -0.0000

Data Index: 831124 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1537287 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1065. Min Act: -0.0000

Data Index: 967520 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1202. Min Act: -0.0000

Data Index: 903281 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1386642 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1032. Min Act: -0.0000

Data Index: 112725 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1548777 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1053230 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.0969. Min Act: -0.0000

Data Index: 677368 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1420677 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1458043 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1438501 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1362560 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.0904. Min Act: -0.0000

Data Index: 563173 (C4 (Web Text))

Max Activating Token Index: 398