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

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

Neuron 4156 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: 1.5727. Min Range: -1.5727

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1337713 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.4220. Min Act: -0.0000

Data Index: 845072 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3208. Min Act: -0.0000

Data Index: 349001 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1100087 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1602537 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2864. Min Act: -0.0000

Data Index: 977436 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2031. Min Act: -0.0000

Data Index: 636322 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1878. Min Act: -0.0000

Data Index: 945117 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1076699 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2435. Min Act: -0.0000

Data Index: 404374 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1670. Min Act: -0.0000

Data Index: 155919 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2062. Min Act: -0.0000

Data Index: 971880 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1019748 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1755. Min Act: -0.0000

Data Index: 714221 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1220470 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1604. Min Act: -0.0000

Data Index: 875376 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1009436 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.0929. Min Act: -0.0000

Data Index: 791028 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.0698. Min Act: -0.0000

Data Index: 482543 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1503. Min Act: -0.0000

Data Index: 91802 (C4 (Web Text))

Max Activating Token Index: 496