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

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

Neuron 2526 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3864. Min Act: -0.0001

Data Index: 304022 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4667. Min Act: -0.0001

Data Index: 374270 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4218. Min Act: -0.0001

Data Index: 585178 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2934. Min Act: -0.0001

Data Index: 615892 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2836. Min Act: -0.0001

Data Index: 133728 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2687. Min Act: -0.0001

Data Index: 425964 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1327. Min Act: -0.0001

Data Index: 297559 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1732. Min Act: -0.0001

Data Index: 110432 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1652. Min Act: -0.0001

Data Index: 974913 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1709. Min Act: -0.0001

Data Index: 771275 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1140. Min Act: -0.0001

Data Index: 1131633 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1300. Min Act: -0.0001

Data Index: 743410 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1775. Min Act: -0.0001

Data Index: 1041387 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1229. Min Act: -0.0001

Data Index: 820439 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0323. Min Act: -0.0001

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.4667. Min Range: -1.4667

Max Act: 0.9630. Min Act: -0.0001

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 1.4667. Min Range: -1.4667

Max Act: 0.9854. Min Act: -0.0001

Data Index: 849343 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.4667. Min Range: -1.4667

Max Act: 0.9300. Min Act: -0.0001

Data Index: 373677 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0229. Min Act: -0.0001

Data Index: 709736 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.4667. Min Range: -1.4667

Max Act: 0.9638. Min Act: -0.0001

Data Index: 204821 (C4 (Web Text))

Max Activating Token Index: 470