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

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

Neuron 1525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.3025. Min Act: -0.0001

Data Index: 1116166 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.2891. Min Act: -0.0001

Data Index: 649063 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.2503. Min Act: -0.0001

Data Index: 366843 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.2173. Min Act: -0.0001

Data Index: 896236 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.1471. Min Act: -0.0001

Data Index: 1242607 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.2080. Min Act: -0.0001

Data Index: 1125891 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.2182. Min Act: -0.0001

Data Index: 1273824 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.1804. Min Act: -0.0001

Data Index: 554094 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.1070. Min Act: -0.0001

Data Index: 886954 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.0110. Min Act: -0.0001

Data Index: 28654 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9723. Min Act: -0.0001

Data Index: 397899 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.0904. Min Act: -0.0001

Data Index: 120743 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1003285 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9686. Min Act: -0.0001

Data Index: 949649 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9696. Min Act: -0.0001

Data Index: 608217 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.3025. Min Range: -1.3025

Max Act: 1.0120. Min Act: -0.0001

Data Index: 387549 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9356. Min Act: -0.0001

Data Index: 616976 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9708. Min Act: -0.0001

Data Index: 1065828 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.9409. Min Act: -0.0001

Data Index: 418929 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.3025. Min Range: -1.3025

Max Act: 0.6876. Min Act: -0.0001

Data Index: 911735 (C4 (Web Text))

Max Activating Token Index: 78