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

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

Neuron 992 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: 0.4915. Min Range: -0.4915

Max Act: 0.4915. Min Act: -0.0000

Data Index: 313561 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1158410 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4728. Min Act: -0.0000

Data Index: 139491 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1085018 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4593. Min Act: -0.0000

Data Index: 53052 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4262. Min Act: -0.0000

Data Index: 329896 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4145. Min Act: -0.0000

Data Index: 547911 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1306938 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4374. Min Act: -0.0000

Data Index: 380364 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4053. Min Act: -0.0000

Data Index: 216532 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3735. Min Act: -0.0000

Data Index: 341520 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3766. Min Act: -0.0000

Data Index: 493348 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3638. Min Act: -0.0000

Data Index: 912481 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1076125 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4203. Min Act: -0.0000

Data Index: 340353 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1056693 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3854. Min Act: 0.0000

Data Index: 195749 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3803. Min Act: -0.0000

Data Index: 124357 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3437. Min Act: -0.0000

Data Index: 27488 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3674. Min Act: -0.0000

Data Index: 96934 (C4 (Web Text))

Max Activating Token Index: 929