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

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

Neuron 3130 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.8678. Min Act: -0.0000

Data Index: 994313 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.6660. Min Act: -0.0000

Data Index: 951311 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.6342. Min Act: -0.0000

Data Index: 207869 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.7217. Min Act: -0.0000

Data Index: 533771 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.5509. Min Act: -0.0000

Data Index: 694850 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.5389. Min Act: -0.0000

Data Index: 283981 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3831. Min Act: -0.0000

Data Index: 1304394 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.5033. Min Act: -0.0000

Data Index: 831085 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.4869. Min Act: -0.0000

Data Index: 911867 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3684. Min Act: -0.0000

Data Index: 199711 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2773. Min Act: -0.0000

Data Index: 323436 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3938. Min Act: -0.0000

Data Index: 1283902 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1031750 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.4084. Min Act: -0.0000

Data Index: 414579 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2637. Min Act: -0.0000

Data Index: 309596 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3756. Min Act: -0.0000

Data Index: 194351 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3909. Min Act: -0.0000

Data Index: 925863 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3988. Min Act: -0.0000

Data Index: 846034 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.5123. Min Act: -0.0000

Data Index: 233489 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3704. Min Act: -0.0000

Data Index: 2674 (C4 (Web Text))

Max Activating Token Index: 131