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

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

Neuron 1618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5666. Min Range: -6.5666

Max Act: 6.5666. Min Act: -0.0000

Data Index: 408217 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.9061. Min Act: -0.0000

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.6981. Min Act: -0.0000

Data Index: 1129069 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.7796. Min Act: -0.0000

Data Index: 1244410 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.6390. Min Act: -0.0001

Data Index: 461140 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.2890. Min Act: -0.0000

Data Index: 597815 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.8245. Min Act: -0.0000

Data Index: 819322 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.2000. Min Act: -0.0000

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.3615. Min Act: -0.0000

Data Index: 1315035 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.6286. Min Act: -0.0000

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.2479. Min Act: -0.0000

Data Index: 342004 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.0700. Min Act: -0.0000

Data Index: 827290 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.4220. Min Act: -0.0000

Data Index: 1265384 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.0684. Min Act: -0.0001

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.4004. Min Act: -0.0000

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.1798. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.3476. Min Act: -0.0000

Data Index: 1201648 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.3235. Min Act: -0.0000

Data Index: 366897 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.0792. Min Act: -0.0000

Data Index: 298449 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 6.5666. Min Range: -6.5666

Max Act: 5.4372. Min Act: -0.0000

Data Index: 635581 (C4 (Web Text))

Max Activating Token Index: 600