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

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

Neuron 3714 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1201. Min Range: -1.1201

Max Act: 1.1201. Min Act: -0.0000

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 1.1201. Min Range: -1.1201

Max Act: 1.0812. Min Act: -0.0000

Data Index: 514924 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.1201. Min Range: -1.1201

Max Act: 1.1153. Min Act: -0.0000

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.1201. Min Range: -1.1201

Max Act: 1.0489. Min Act: -0.0000

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9654. Min Act: -0.0000

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1318900 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9414. Min Act: -0.0000

Data Index: 648920 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9978. Min Act: -0.0000

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8598. Min Act: -0.0000

Data Index: 88224 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9709. Min Act: -0.0000

Data Index: 827260 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7766. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1059972 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8305. Min Act: -0.0000

Data Index: 935841 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8725. Min Act: -0.0000

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7449. Min Act: -0.0000

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7519. Min Act: -0.0000

Data Index: 105627 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7413. Min Act: -0.0000

Data Index: 980745 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7461. Min Act: -0.0000

Data Index: 399677 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1048574 (C4 (Web Text))

Max Activating Token Index: 124