Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.5327. Min Act: -0.0000

Data Index: 48301 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.5194. Min Act: -0.0000

Data Index: 718752 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4209. Min Act: -0.0000

Data Index: 741646 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1321819 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4242. Min Act: -0.0000

Data Index: 410674 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1192352 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4002. Min Act: -0.0001

Data Index: 851096 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4275. Min Act: -0.0001

Data Index: 1149469 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.3933. Min Act: -0.0000

Data Index: 4328 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4051. Min Act: -0.0000

Data Index: 949483 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4178. Min Act: -0.0000

Data Index: 314162 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4049. Min Act: -0.0001

Data Index: 910597 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4057. Min Act: -0.0001

Data Index: 45265 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4000. Min Act: -0.0000

Data Index: 558990 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1225899 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1119865 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4089. Min Act: -0.0000

Data Index: 272069 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.3838. Min Act: -0.0000

Data Index: 584915 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.3811. Min Act: -0.0001

Data Index: 294515 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.5327. Min Range: -0.5327

Max Act: 0.4040. Min Act: -0.0000

Data Index: 114973 (C4 (Web Text))

Max Activating Token Index: 756