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

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

Neuron 4470 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: 1.2896. Min Range: -1.2896

Max Act: 1.2896. Min Act: -0.0000

Data Index: 711332 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1167756 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2038. Min Act: -0.0000

Data Index: 111918 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2147. Min Act: -0.0000

Data Index: 120723 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1332175 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1880. Min Act: -0.0000

Data Index: 468710 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1585. Min Act: -0.0000

Data Index: 565331 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1545. Min Act: -0.0000

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1128. Min Act: -0.0000

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0537. Min Act: -0.0000

Data Index: 783930 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1403. Min Act: -0.0000

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1310. Min Act: -0.0000

Data Index: 748714 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1130. Min Act: -0.0000

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0728. Min Act: -0.0000

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 1.2896. Min Range: -1.2896

Max Act: 0.9636. Min Act: -0.0000

Data Index: 682569 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0928. Min Act: -0.0000

Data Index: 962644 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0601. Min Act: -0.0000

Data Index: 884839 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0885. Min Act: -0.0000

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.0292. Min Act: -0.0000

Data Index: 174048 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.2896. Min Range: -1.2896

Max Act: 0.9459. Min Act: -0.0000

Data Index: 390811 (C4 (Web Text))

Max Activating Token Index: 343