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

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

Neuron 3591 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: 1.0105. Min Range: -1.0105

Max Act: 1.0105. Min Act: -0.0000

Data Index: 473050 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1111490 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1212387 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1301969 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7863. Min Act: -0.0000

Data Index: 105490 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1245969 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6958. Min Act: -0.0000

Data Index: 635120 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7510. Min Act: -0.0000

Data Index: 291575 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6769. Min Act: -0.0000

Data Index: 522842 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6216. Min Act: -0.0000

Data Index: 983359 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6642. Min Act: -0.0000

Data Index: 817781 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6348. Min Act: -0.0000

Data Index: 105189 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1029937 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6597. Min Act: -0.0000

Data Index: 985120 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1302487 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6545. Min Act: -0.0000

Data Index: 821556 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6296. Min Act: -0.0000

Data Index: 839823 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6222. Min Act: -0.0000

Data Index: 895636 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6189. Min Act: -0.0000

Data Index: 822773 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1054995 (C4 (Web Text))

Max Activating Token Index: 220