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

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

Neuron 3041 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6202. Min Act: -0.0001

Data Index: 122012 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6972. Min Act: -0.0001

Data Index: 925161 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5950. Min Act: -0.0001

Data Index: 766939 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5424. Min Act: -0.0001

Data Index: 450696 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.7483. Min Act: -0.0001

Data Index: 88547 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.6065. Min Act: -0.0001

Data Index: 1033161 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.5464. Min Act: -0.0001

Data Index: 29076 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4902. Min Act: -0.0001

Data Index: 668693 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2873. Min Act: -0.0001

Data Index: 1145290 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.1544. Min Act: -0.0001

Data Index: 350764 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2899. Min Act: -0.0001

Data Index: 1304921 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3012. Min Act: -0.0001

Data Index: 866990 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2593. Min Act: -0.0001

Data Index: 1245039 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2649. Min Act: -0.0001

Data Index: 846526 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2212. Min Act: -0.0001

Data Index: 713021 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.0828. Min Act: -0.0001

Data Index: 499718 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.0854. Min Act: -0.0001

Data Index: 1135647 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2282. Min Act: -0.0001

Data Index: 358222 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2311. Min Act: -0.0001

Data Index: 1199095 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.0577. Min Act: -0.0001

Data Index: 1318618 (C4 (Web Text))

Max Activating Token Index: 758