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

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

Neuron 3326 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: 3.5574. Min Range: -3.5574

Max Act: 3.5574. Min Act: -0.0000

Data Index: 1245816 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.4701. Min Act: -0.0000

Data Index: 271824 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.4841. Min Act: -0.0000

Data Index: 623047 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3039. Min Act: -0.0000

Data Index: 173205 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.2433. Min Act: -0.0000

Data Index: 1261901 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.1652. Min Act: -0.0000

Data Index: 33219 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.2859. Min Act: -0.0000

Data Index: 496319 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8391. Min Act: -0.0000

Data Index: 377282 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8480. Min Act: -0.0000

Data Index: 1355894 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8126. Min Act: -0.0000

Data Index: 341309 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.9298. Min Act: -0.0000

Data Index: 1115604 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8805. Min Act: -0.0000

Data Index: 169085 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8741. Min Act: -0.0000

Data Index: 49147 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8458. Min Act: -0.0000

Data Index: 512826 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1348774 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.6795. Min Act: -0.0000

Data Index: 374636 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.7045. Min Act: -0.0000

Data Index: 420799 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8049. Min Act: -0.0000

Data Index: 198312 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.9266. Min Act: -0.0000

Data Index: 730 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.5574. Min Range: -3.5574

Max Act: 2.8137. Min Act: -0.0000

Data Index: 468787 (C4 (Web Text))

Max Activating Token Index: 1019