Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2238. Min Range: -3.2238

Max Act: 3.2238. Min Act: -0.0000

Data Index: 758412 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.8723. Min Act: -0.0000

Data Index: 14974 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.8660. Min Act: -0.0000

Data Index: 203935 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.8584. Min Act: -0.0000

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.6257. Min Act: -0.0000

Data Index: 765156 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.4965. Min Act: -0.0000

Data Index: 836303 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.2881. Min Act: -0.0000

Data Index: 594535 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1103734 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.3736. Min Act: -0.0000

Data Index: 1088607 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.3519. Min Act: -0.0000

Data Index: 1239048 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1266434 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.0953. Min Act: -0.0000

Data Index: 13424 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1894. Min Act: -0.0000

Data Index: 1125148 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1759. Min Act: -0.0000

Data Index: 808348 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1661. Min Act: -0.0000

Data Index: 1078023 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1659. Min Act: -0.0000

Data Index: 1117715 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1284737 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.2354. Min Act: -0.0000

Data Index: 221938 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 3.2238. Min Range: -3.2238

Max Act: 2.1091. Min Act: -0.0000

Data Index: 759738 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.2238. Min Range: -3.2238

Max Act: 1.9732. Min Act: -0.0000

Data Index: 689256 (C4 (Web Text))

Max Activating Token Index: 435