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

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

Neuron 4314 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0890. Min Range: -2.0890

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1335264 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9430. Min Act: -0.0000

Data Index: 634014 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 2.0890. Min Range: -2.0890

Max Act: 2.0592. Min Act: -0.0000

Data Index: 532533 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9451. Min Act: -0.0000

Data Index: 1253138 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8232. Min Act: -0.0000

Data Index: 1224139 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 2.0890. Min Range: -2.0890

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1199055 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9104. Min Act: -0.0000

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8956. Min Act: -0.0000

Data Index: 102477 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8369. Min Act: -0.0000

Data Index: 344418 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8352. Min Act: -0.0000

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9318. Min Act: -0.0000

Data Index: 626810 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9300. Min Act: -0.0000

Data Index: 47024 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8752. Min Act: -0.0000

Data Index: 1123438 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7599. Min Act: -0.0000

Data Index: 280338 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7705. Min Act: -0.0000

Data Index: 894605 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8712. Min Act: -0.0000

Data Index: 144070 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9244. Min Act: -0.0000

Data Index: 293699 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8497. Min Act: -0.0000

Data Index: 1334717 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8656. Min Act: -0.0000

Data Index: 1093612 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8530. Min Act: -0.0000

Data Index: 734723 (C4 (Web Text))

Max Activating Token Index: 664