Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.1156. Min Act: -0.0001

Data Index: 975823 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9991. Min Act: -0.0000

Data Index: 923976 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0351. Min Act: -0.0000

Data Index: 326760 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0128. Min Act: -0.0001

Data Index: 288671 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9547. Min Act: -0.0001

Data Index: 858879 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0140. Min Act: -0.0001

Data Index: 1221615 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9925. Min Act: -0.0000

Data Index: 141938 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9202. Min Act: -0.0000

Data Index: 638303 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9086. Min Act: -0.0000

Data Index: 285319 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8515. Min Act: -0.0000

Data Index: 544833 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8747. Min Act: -0.0000

Data Index: 349810 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8846. Min Act: -0.0000

Data Index: 814009 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9692. Min Act: -0.0000

Data Index: 535502 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8783. Min Act: -0.0001

Data Index: 485001 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8716. Min Act: -0.0000

Data Index: 708637 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8378. Min Act: -0.0000

Data Index: 706491 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8903. Min Act: -0.0000

Data Index: 796630 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1202720 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8558. Min Act: -0.0000

Data Index: 194390 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.8323. Min Act: -0.0000

Data Index: 581601 (C4 (Web Text))

Max Activating Token Index: 319