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

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

Neuron 3108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2908. Min Act: -0.0001

Data Index: 533458 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2734. Min Act: -0.0000

Data Index: 680125 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2808. Min Act: -0.0000

Data Index: 860978 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1021. Min Act: -0.0000

Data Index: 627453 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2445. Min Act: -0.0000

Data Index: 523244 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1231718 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1550. Min Act: -0.0000

Data Index: 615462 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1470. Min Act: -0.0001

Data Index: 298593 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1312. Min Act: -0.0000

Data Index: 946119 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1530. Min Act: -0.0000

Data Index: 195808 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0853. Min Act: -0.0000

Data Index: 335580 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1062339 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0487. Min Act: -0.0000

Data Index: 236520 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0227. Min Act: -0.0000

Data Index: 643393 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1315. Min Act: -0.0000

Data Index: 304928 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9906. Min Act: -0.0000

Data Index: 588943 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0532. Min Act: -0.0000

Data Index: 851036 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1335670 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0132. Min Act: -0.0000

Data Index: 372368 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1262319 (C4 (Web Text))

Max Activating Token Index: 988