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

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

Neuron 5925 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5294. Min Range: -4.5294

Max Act: 4.5294. Min Act: -0.0000

Data Index: 36894 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.9493. Min Act: -0.0000

Data Index: 177255 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.8927. Min Act: -0.0000

Data Index: 500109 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 4.5294. Min Range: -4.5294

Max Act: 4.1503. Min Act: -0.0000

Data Index: 1240368 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 4.5294. Min Range: -4.5294

Max Act: 4.0978. Min Act: -0.0000

Data Index: 959790 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.8431. Min Act: -0.0000

Data Index: 1254551 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.7431. Min Act: -0.0000

Data Index: 557503 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 4.5294. Min Range: -4.5294

Max Act: 4.0426. Min Act: -0.0000

Data Index: 1128403 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.8604. Min Act: -0.0000

Data Index: 743170 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.8179. Min Act: -0.0000

Data Index: 94262 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.4718. Min Act: -0.0000

Data Index: 63704 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.6771. Min Act: -0.0000

Data Index: 1233333 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.3883. Min Act: -0.0000

Data Index: 1342846 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.4846. Min Act: -0.0000

Data Index: 1182614 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.6355. Min Act: -0.0000

Data Index: 629945 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.4066. Min Act: -0.0000

Data Index: 367504 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.2069. Min Act: -0.0000

Data Index: 21271 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.4998. Min Act: -0.0000

Data Index: 992902 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.3164. Min Act: -0.0000

Data Index: 961422 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 4.5294. Min Range: -4.5294

Max Act: 3.1445. Min Act: -0.0000

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 58