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

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

Neuron 1497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1010. Min Range: -5.1010

Max Act: 4.7731. Min Act: -0.0000

Data Index: 1267794 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 5.1010. Min Range: -5.1010

Max Act: 5.1010. Min Act: -0.0000

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 5.1010. Min Range: -5.1010

Max Act: 4.6598. Min Act: -0.0000

Data Index: 813091 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 5.1010. Min Range: -5.1010

Max Act: 4.4561. Min Act: -0.0000

Data Index: 90558 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.7071. Min Act: -0.0000

Data Index: 473861 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.8269. Min Act: -0.0000

Data Index: 108614 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.7873. Min Act: -0.0000

Data Index: 106353 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.4476. Min Act: -0.0000

Data Index: 603246 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.2218. Min Act: -0.0000

Data Index: 1106273 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.6744. Min Act: -0.0000

Data Index: 1221197 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.8273. Min Act: -0.0000

Data Index: 1166969 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.4641. Min Act: -0.0000

Data Index: 1203575 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.1063. Min Act: -0.0000

Data Index: 850607 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.3700. Min Act: -0.0000

Data Index: 717119 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.6975. Min Act: -0.0000

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.4923. Min Act: -0.0000

Data Index: 71209 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.3024. Min Act: -0.0000

Data Index: 852137 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.3916. Min Act: -0.0000

Data Index: 630412 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.3637. Min Act: -0.0000

Data Index: 337477 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 5.1010. Min Range: -5.1010

Max Act: 3.2251. Min Act: -0.0000

Data Index: 395851 (C4 (Web Text))

Max Activating Token Index: 1012