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

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

Neuron 3946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1455. Min Range: -3.1455

Max Act: 3.1455. Min Act: -0.0000

Data Index: 790823 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 3.1455. Min Range: -3.1455

Max Act: 2.1789. Min Act: -0.0000

Data Index: 156858 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.8418. Min Act: -0.0000

Data Index: 1087857 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.9228. Min Act: -0.0001

Data Index: 534368 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1091512 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.7073. Min Act: -0.0000

Data Index: 513483 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6844. Min Act: -0.0000

Data Index: 60043 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6572. Min Act: -0.0000

Data Index: 54770 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6494. Min Act: -0.0000

Data Index: 28715 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1331261 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6535. Min Act: -0.0000

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.5483. Min Act: -0.0000

Data Index: 981485 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1110032 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.5073. Min Act: -0.0000

Data Index: 81127 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.4810. Min Act: -0.0000

Data Index: 1137181 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.6646. Min Act: -0.0000

Data Index: 752494 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.3859. Min Act: -0.0000

Data Index: 714649 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.3570. Min Act: -0.0000

Data Index: 426520 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1309175 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 3.1455. Min Range: -3.1455

Max Act: 1.3278. Min Act: -0.0001

Data Index: 350844 (C4 (Web Text))

Max Activating Token Index: 284