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

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

Neuron 4889 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1119085 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5850. Min Act: -0.0001

Data Index: 16024 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5997. Min Act: -0.0001

Data Index: 53333 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5802. Min Act: -0.0001

Data Index: 803353 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4911. Min Act: -0.0001

Data Index: 826707 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5195. Min Act: -0.0001

Data Index: 611581 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5684. Min Act: -0.0001

Data Index: 825612 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4785. Min Act: -0.0001

Data Index: 701000 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1086426 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4483. Min Act: -0.0001

Data Index: 60171 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4870. Min Act: -0.0001

Data Index: 235730 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4703. Min Act: -0.0001

Data Index: 1004438 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5001. Min Act: -0.0001

Data Index: 696597 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4603. Min Act: -0.0001

Data Index: 635877 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5232. Min Act: -0.0001

Data Index: 617401 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4227. Min Act: -0.0001

Data Index: 126961 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4606. Min Act: -0.0001

Data Index: 230009 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4374. Min Act: -0.0001

Data Index: 640403 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.3285. Min Act: -0.0001

Data Index: 72831 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4658. Min Act: -0.0001

Data Index: 806521 (C4 (Web Text))

Max Activating Token Index: 894