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

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

Neuron 2838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3510. Min Act: -0.0000

Data Index: 342324 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3138. Min Act: -0.0000

Data Index: 471398 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3100. Min Act: -0.0000

Data Index: 956604 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1028201 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3033. Min Act: -0.0000

Data Index: 857534 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3004. Min Act: -0.0000

Data Index: 837186 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1222107 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1222706 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2923. Min Act: -0.0000

Data Index: 263940 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1092170 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2873. Min Act: -0.0000

Data Index: 972988 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1033318 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2744. Min Act: -0.0000

Data Index: 828360 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2778. Min Act: -0.0000

Data Index: 145466 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2731. Min Act: -0.0000

Data Index: 215328 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2834. Min Act: 0.0000

Data Index: 829007 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1328258 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2925. Min Act: -0.0001

Data Index: 676566 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2760. Min Act: -0.0000

Data Index: 2319 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1089529 (C4 (Web Text))

Max Activating Token Index: 272