Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0000

Data Index: 688622 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1182. Min Act: -0.0000

Data Index: 203964 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1146. Min Act: -0.0000

Data Index: 16853 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1100. Min Act: -0.0000

Data Index: 855613 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1046. Min Act: -0.0000

Data Index: 366701 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0894. Min Act: -0.0000

Data Index: 825811 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1034. Min Act: -0.0000

Data Index: 619665 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0987. Min Act: -0.0000

Data Index: 107656 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0804. Min Act: -0.0000

Data Index: 522455 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0969. Min Act: -0.0000

Data Index: 788349 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0968. Min Act: -0.0000

Data Index: 351623 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1288455 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1184909 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0839. Min Act: -0.0000

Data Index: 170035 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0805. Min Act: -0.0000

Data Index: 415288 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0812. Min Act: -0.0000

Data Index: 112274 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0808. Min Act: -0.0000

Data Index: 50658 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0830. Min Act: -0.0000

Data Index: 897017 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0792. Min Act: -0.0000

Data Index: 326570 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0708. Min Act: -0.0000

Data Index: 893740 (C4 (Web Text))

Max Activating Token Index: 892