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

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

Neuron 1038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1538813 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1355664 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1706. Min Act: -0.0000

Data Index: 435953 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1279656 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1295966 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9630. Min Act: -0.0000

Data Index: 906462 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1244497 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1271142 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1372461 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8882. Min Act: -0.0000

Data Index: 905809 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8289. Min Act: -0.0000

Data Index: 70438 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8700. Min Act: -0.0000

Data Index: 874789 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8603. Min Act: -0.0000

Data Index: 42281 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8658. Min Act: -0.0000

Data Index: 642752 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8037. Min Act: -0.0000

Data Index: 960735 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1245211 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8303. Min Act: -0.0000

Data Index: 667742 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8601. Min Act: -0.0000

Data Index: 958083 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8436. Min Act: -0.0000

Data Index: 557593 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.7653. Min Act: -0.0000

Data Index: 601366 (C4 (Web Text))

Max Activating Token Index: 840