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

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

Neuron 4002 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: 4.9698. Min Range: -4.9698

Max Act: 4.9396. Min Act: -0.0000

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.9698. Min Act: -0.0000

Data Index: 830060 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.3315. Min Act: -0.0000

Data Index: 1108347 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.6095. Min Act: -0.0000

Data Index: 741714 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.5305. Min Act: -0.0000

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.3174. Min Act: -0.0000

Data Index: 651788 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.4591. Min Act: -0.0000

Data Index: 540446 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.3698. Min Act: -0.0000

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.4867. Min Act: -0.0000

Data Index: 94344 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.0874. Min Act: -0.0000

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.0659. Min Act: -0.0000

Data Index: 924948 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.2471. Min Act: -0.0000

Data Index: 1194688 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 4.9698. Min Range: -4.9698

Max Act: 3.9926. Min Act: -0.0000

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.3188. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.1478. Min Act: -0.0000

Data Index: 1124506 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.1530. Min Act: -0.0000

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.1149. Min Act: -0.0000

Data Index: 732006 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.1366. Min Act: -0.0000

Data Index: 937887 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.4448. Min Act: -0.0000

Data Index: 469804 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 4.9698. Min Range: -4.9698

Max Act: 4.1026. Min Act: -0.0000

Data Index: 1060735 (C4 (Web Text))

Max Activating Token Index: 981