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

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

Neuron 1135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0897. Min Range: -2.0897

Max Act: 2.0897. Min Act: -0.0000

Data Index: 1144981 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 2.0897. Min Range: -2.0897

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.0897. Min Range: -2.0897

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1242163 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.9683. Min Act: -0.0000

Data Index: 145905 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.8589. Min Act: -0.0000

Data Index: 104986 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.8017. Min Act: -0.0000

Data Index: 994900 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7946. Min Act: -0.0000

Data Index: 303300 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1245244 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1200353 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7605. Min Act: -0.0000

Data Index: 727596 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7670. Min Act: -0.0000

Data Index: 754765 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7256. Min Act: -0.0000

Data Index: 999918 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.8167. Min Act: -0.0000

Data Index: 265735 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7640. Min Act: -0.0000

Data Index: 729350 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1209610 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7593. Min Act: -0.0000

Data Index: 369680 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.8427. Min Act: -0.0000

Data Index: 914671 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1192682 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.6536. Min Act: -0.0000

Data Index: 260459 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 2.0897. Min Range: -2.0897

Max Act: 1.7108. Min Act: -0.0000

Data Index: 694673 (C4 (Web Text))

Max Activating Token Index: 760