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

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

Neuron 863 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: 0.6098. Min Range: -0.6098

Max Act: 0.6037. Min Act: -0.0000

Data Index: 958465 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1174801 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1193868 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1075636 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4944. Min Act: -0.0000

Data Index: 666006 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1192883 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3915. Min Act: -0.0000

Data Index: 227763 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1025632 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1009713 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4115. Min Act: -0.0000

Data Index: 486067 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1053619 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3683. Min Act: -0.0000

Data Index: 714130 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3320. Min Act: -0.0000

Data Index: 382506 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3635. Min Act: -0.0000

Data Index: 756483 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3288. Min Act: -0.0000

Data Index: 750889 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3134. Min Act: -0.0000

Data Index: 353171 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1352029 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.2870. Min Act: -0.0000

Data Index: 890606 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.2959. Min Act: -0.0000

Data Index: 232328 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1338600 (C4 (Web Text))

Max Activating Token Index: 306