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

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

Neuron 1681 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: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0002

Data Index: 936779 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6724. Min Act: -0.0002

Data Index: 359038 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6459. Min Act: -0.0001

Data Index: 631597 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6443. Min Act: -0.0002

Data Index: 1278785 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6118. Min Act: -0.0001

Data Index: 323400 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1255175 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5972. Min Act: -0.0002

Data Index: 728645 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5578. Min Act: -0.0002

Data Index: 1332854 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6042. Min Act: -0.0001

Data Index: 301235 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1316384 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5911. Min Act: -0.0002

Data Index: 1021110 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6097. Min Act: -0.0002

Data Index: 604272 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5845. Min Act: -0.0002

Data Index: 1242357 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1271268 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5659. Min Act: -0.0002

Data Index: 1223482 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5398. Min Act: -0.0002

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5546. Min Act: -0.0002

Data Index: 249108 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5761. Min Act: -0.0001

Data Index: 353794 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5753. Min Act: -0.0001

Data Index: 29511 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5498. Min Act: -0.0001

Data Index: 366864 (C4 (Web Text))

Max Activating Token Index: 42