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

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

Neuron 3480 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0003

Data Index: 644394 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5521. Min Act: -0.0003

Data Index: 323159 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5355. Min Act: -0.0003

Data Index: 311900 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4971. Min Act: -0.0003

Data Index: 870770 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4905. Min Act: -0.0002

Data Index: 265507 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4592. Min Act: -0.0002

Data Index: 676262 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4123. Min Act: -0.0002

Data Index: 1147891 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3984. Min Act: -0.0002

Data Index: 1329920 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3957. Min Act: -0.0002

Data Index: 557454 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3835. Min Act: -0.0003

Data Index: 254375 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3752. Min Act: -0.0003

Data Index: 845075 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3327. Min Act: -0.0003

Data Index: 354482 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3258. Min Act: -0.0003

Data Index: 67491 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3425. Min Act: -0.0002

Data Index: 744565 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3396. Min Act: -0.0003

Data Index: 1223051 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3385. Min Act: -0.0003

Data Index: 1280687 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3372. Min Act: -0.0002

Data Index: 301636 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3252. Min Act: -0.0003

Data Index: 5419 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3165. Min Act: -0.0003

Data Index: 320831 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3162. Min Act: -0.0003

Data Index: 799004 (C4 (Web Text))

Max Activating Token Index: 530