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

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

Neuron 2555 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: 0.6581. Min Range: -0.6581

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1004057 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6250. Min Act: -0.0002

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6029. Min Act: -0.0001

Data Index: 820315 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6185. Min Act: -0.0002

Data Index: 574229 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5630. Min Act: -0.0001

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5420. Min Act: -0.0002

Data Index: 1272125 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5338. Min Act: -0.0002

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5303. Min Act: -0.0002

Data Index: 709895 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5435. Min Act: -0.0001

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5299. Min Act: -0.0001

Data Index: 427180 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5273. Min Act: -0.0002

Data Index: 726401 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.6141. Min Act: -0.0002

Data Index: 365649 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5328. Min Act: -0.0002

Data Index: 289962 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5120. Min Act: -0.0002

Data Index: 416626 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5005. Min Act: -0.0002

Data Index: 1128452 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5121. Min Act: -0.0002

Data Index: 366425 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5251. Min Act: -0.0002

Data Index: 804363 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4805. Min Act: -0.0002

Data Index: 987305 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4642. Min Act: -0.0001

Data Index: 976260 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4933. Min Act: -0.0002

Data Index: 1198673 (C4 (Web Text))

Max Activating Token Index: 979