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

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

Neuron 3503 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: 4.5881. Min Range: -4.5881

Max Act: 4.5881. Min Act: -0.0000

Data Index: 1026028 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.2489. Min Act: -0.0000

Data Index: 26951 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.9208. Min Act: -0.0000

Data Index: 791355 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1606. Min Act: -0.0000

Data Index: 1315503 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.9679. Min Act: -0.0000

Data Index: 1136001 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1167. Min Act: -0.0000

Data Index: 1018611 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.8856. Min Act: -0.0000

Data Index: 1259072 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.6396. Min Act: -0.0000

Data Index: 286723 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.7299. Min Act: -0.0000

Data Index: 1145376 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.7043. Min Act: -0.0000

Data Index: 885144 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.6149. Min Act: -0.0000

Data Index: 457706 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.4496. Min Act: -0.0000

Data Index: 595994 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.5985. Min Act: -0.0000

Data Index: 544028 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.3240. Min Act: -0.0000

Data Index: 615255 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.6039. Min Act: -0.0000

Data Index: 488927 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.2787. Min Act: -0.0000

Data Index: 1171853 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.2616. Min Act: -0.0000

Data Index: 1217465 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.3999. Min Act: -0.0000

Data Index: 386890 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.5584. Min Act: -0.0000

Data Index: 819644 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.2150. Min Act: -0.0000

Data Index: 656010 (C4 (Web Text))

Max Activating Token Index: 296