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

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

Neuron 2720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5306. Min Act: -0.0002

Data Index: 497037 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5610. Min Act: -0.0001

Data Index: 950692 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5199. Min Act: -0.0001

Data Index: 111026 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5049. Min Act: -0.0001

Data Index: 1271574 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5112. Min Act: -0.0001

Data Index: 1058515 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5265. Min Act: -0.0002

Data Index: 668264 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5180. Min Act: -0.0001

Data Index: 506454 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3960. Min Act: -0.0001

Data Index: 368985 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4919. Min Act: -0.0001

Data Index: 460654 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4734. Min Act: -0.0001

Data Index: 1353023 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3233. Min Act: -0.0001

Data Index: 503614 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3183. Min Act: -0.0002

Data Index: 119113 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5711. Min Act: -0.0001

Data Index: 56409 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1197371 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1108749 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5724. Min Act: -0.0001

Data Index: 1144047 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4455. Min Act: -0.0001

Data Index: 616143 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.3754. Min Act: -0.0001

Data Index: 885132 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4109. Min Act: -0.0002

Data Index: 1260968 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5626. Min Act: -0.0002

Data Index: 314676 (C4 (Web Text))

Max Activating Token Index: 666