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

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

Neuron 3800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1127. Min Act: -0.0000

Data Index: 839655 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1279. Min Act: -0.0000

Data Index: 669433 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0807. Min Act: -0.0000

Data Index: 702350 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1314359 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0583. Min Act: -0.0000

Data Index: 731303 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0633. Min Act: -0.0000

Data Index: 599243 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1228689 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1105678 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1161101 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0069. Min Act: -0.0000

Data Index: 347078 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9009. Min Act: -0.0000

Data Index: 360058 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9879. Min Act: -0.0000

Data Index: 490355 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9491. Min Act: -0.0000

Data Index: 196079 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9154. Min Act: -0.0000

Data Index: 943882 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8827. Min Act: -0.0000

Data Index: 567139 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9557. Min Act: -0.0000

Data Index: 19419 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9735. Min Act: -0.0000

Data Index: 807119 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8818. Min Act: -0.0000

Data Index: 338479 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8818. Min Act: -0.0000

Data Index: 923836 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8818. Min Act: -0.0000

Data Index: 692545 (C4 (Web Text))

Max Activating Token Index: 7