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

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

Neuron 3662 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2953. Min Range: -2.2953

Max Act: 2.2953. Min Act: -0.0000

Data Index: 758742 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.8043. Min Act: -0.0000

Data Index: 811752 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.6359. Min Act: -0.0000

Data Index: 744403 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.5899. Min Act: -0.0000

Data Index: 982530 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1313839 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.6579. Min Act: -0.0000

Data Index: 89415 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.5494. Min Act: -0.0000

Data Index: 401982 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1112986 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.4872. Min Act: -0.0000

Data Index: 849573 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.4425. Min Act: -0.0000

Data Index: 996992 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2965. Min Act: -0.0000

Data Index: 472865 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.3788. Min Act: -0.0000

Data Index: 185592 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1241634 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1004451 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2392. Min Act: -0.0000

Data Index: 381661 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1352786 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.3770. Min Act: -0.0000

Data Index: 124224 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2906. Min Act: -0.0000

Data Index: 792411 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1127 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 2.2953. Min Range: -2.2953

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1345843 (C4 (Web Text))

Max Activating Token Index: 538