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

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

Neuron 3354 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: 2.0729. Min Range: -2.0729

Max Act: 1.9995. Min Act: -0.0000

Data Index: 830469 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 2.0729. Min Range: -2.0729

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1099752 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.0729. Min Range: -2.0729

Max Act: 2.0155. Min Act: -0.0000

Data Index: 709228 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1075947 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.7458. Min Act: -0.0000

Data Index: 892851 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1289870 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1020119 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5753. Min Act: -0.0000

Data Index: 630382 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.3857. Min Act: -0.0000

Data Index: 609773 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1295553 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5435. Min Act: -0.0000

Data Index: 366027 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.4669. Min Act: -0.0000

Data Index: 885478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5507. Min Act: -0.0000

Data Index: 567739 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5349. Min Act: -0.0000

Data Index: 500819 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.6265. Min Act: -0.0000

Data Index: 1024779 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5184. Min Act: -0.0000

Data Index: 351085 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.4929. Min Act: -0.0000

Data Index: 379930 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1011934 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.5323. Min Act: -0.0000

Data Index: 1034325 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 2.0729. Min Range: -2.0729

Max Act: 1.4327. Min Act: -0.0000

Data Index: 488436 (C4 (Web Text))

Max Activating Token Index: 573