Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3134 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1074. Min Range: -1.1074

Max Act: 1.1074. Min Act: -0.0001

Data Index: 1175125 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.9471. Min Act: -0.0001

Data Index: 823763 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8273. Min Act: -0.0001

Data Index: 450852 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1300743 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8221. Min Act: -0.0001

Data Index: 445265 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8135. Min Act: -0.0001

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8227. Min Act: -0.0001

Data Index: 739946 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7858. Min Act: -0.0001

Data Index: 11756 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7995. Min Act: -0.0001

Data Index: 669087 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7795. Min Act: -0.0001

Data Index: 483832 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.8118. Min Act: -0.0001

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7482. Min Act: -0.0001

Data Index: 1225667 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7074. Min Act: -0.0001

Data Index: 545987 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1258642 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7651. Min Act: -0.0001

Data Index: 721586 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7533. Min Act: -0.0001

Data Index: 305064 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7904. Min Act: -0.0001

Data Index: 369718 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7266. Min Act: -0.0001

Data Index: 301343 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1085316 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.1074. Min Range: -1.1074

Max Act: 0.6875. Min Act: -0.0001

Data Index: 1191830 (C4 (Web Text))

Max Activating Token Index: 521