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

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

Neuron 1438 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: 0.8908. Min Range: -0.8908

Max Act: 0.8403. Min Act: -0.0002

Data Index: 846009 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8908. Min Act: -0.0001

Data Index: 1167366 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7766. Min Act: -0.0001

Data Index: 1233155 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7148. Min Act: -0.0001

Data Index: 328170 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8469. Min Act: -0.0001

Data Index: 135470 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8503. Min Act: -0.0001

Data Index: 943962 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7626. Min Act: -0.0002

Data Index: 176625 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7810. Min Act: -0.0002

Data Index: 1332860 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7869. Min Act: -0.0001

Data Index: 534730 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8094. Min Act: -0.0002

Data Index: 774338 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8165. Min Act: -0.0001

Data Index: 912313 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7954. Min Act: -0.0001

Data Index: 1173821 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7228. Min Act: -0.0001

Data Index: 1011095 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7180. Min Act: -0.0001

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.6684. Min Act: -0.0002

Data Index: 49927 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1351688 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7628. Min Act: -0.0002

Data Index: 144808 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7800. Min Act: -0.0001

Data Index: 718898 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1246550 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8091. Min Act: -0.0002

Data Index: 472695 (C4 (Web Text))

Max Activating Token Index: 795