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

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

Neuron 1009 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.6500. Min Act: -0.0000

Data Index: 1164564 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.8096. Min Act: -0.0000

Data Index: 597888 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.7064. Min Act: -0.0000

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.3196. Min Act: -0.0000

Data Index: 360992 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.4293. Min Act: -0.0000

Data Index: 432938 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.0739. Min Act: -0.0000

Data Index: 1078893 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 4.8096. Min Range: -4.8096

Max Act: 4.0008. Min Act: -0.0000

Data Index: 1114032 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.9953. Min Act: -0.0000

Data Index: 1315543 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.7592. Min Act: -0.0000

Data Index: 1307822 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.8697. Min Act: -0.0000

Data Index: 396316 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.5456. Min Act: -0.0000

Data Index: 107769 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.9967. Min Act: -0.0000

Data Index: 309004 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.6327. Min Act: -0.0000

Data Index: 843634 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.7571. Min Act: -0.0000

Data Index: 691658 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.5605. Min Act: -0.0000

Data Index: 814805 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.5317. Min Act: -0.0000

Data Index: 668975 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.6433. Min Act: -0.0000

Data Index: 42491 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.4667. Min Act: -0.0000

Data Index: 805162 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.3037. Min Act: -0.0000

Data Index: 153587 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 4.8096. Min Range: -4.8096

Max Act: 3.1606. Min Act: -0.0000

Data Index: 1243183 (C4 (Web Text))

Max Activating Token Index: 307