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

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

Neuron 3503 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: 3.1710. Min Range: -3.1710

Max Act: 3.1710. Min Act: -0.0000

Data Index: 1313523 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.5461. Min Act: -0.0000

Data Index: 1171332 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.4017. Min Act: -0.0000

Data Index: 453253 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.5195. Min Act: -0.0000

Data Index: 470035 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.4885. Min Act: -0.0000

Data Index: 183551 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.4090. Min Act: -0.0000

Data Index: 1025261 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2685. Min Act: -0.0000

Data Index: 782158 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2217. Min Act: -0.0000

Data Index: 934076 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.3117. Min Act: -0.0000

Data Index: 570921 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2930. Min Act: -0.0000

Data Index: 177533 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2582. Min Act: -0.0000

Data Index: 955701 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2344. Min Act: -0.0000

Data Index: 1337414 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2171. Min Act: -0.0000

Data Index: 485424 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.1032. Min Act: -0.0000

Data Index: 240656 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2137. Min Act: -0.0000

Data Index: 842954 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.1803. Min Act: -0.0001

Data Index: 98899 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.2835. Min Act: -0.0000

Data Index: 90915 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.3941. Min Act: -0.0000

Data Index: 1298342 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.1590. Min Act: -0.0000

Data Index: 499328 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 3.1710. Min Range: -3.1710

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1357523 (C4 (Web Text))

Max Activating Token Index: 652