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

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

Neuron 539 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0819. Min Range: -1.0819

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1207785 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.0819. Min Range: -1.0819

Max Act: 1.0618. Min Act: -0.0000

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.0819. Min Range: -1.0819

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1267853 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9745. Min Act: -0.0000

Data Index: 196740 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9400. Min Act: -0.0000

Data Index: 485429 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9243. Min Act: -0.0000

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8947. Min Act: -0.0000

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9594. Min Act: -0.0000

Data Index: 555193 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1355978 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.0819. Min Range: -1.0819

Max Act: 1.0573. Min Act: -0.0000

Data Index: 579227 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1502710 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8938. Min Act: -0.0000

Data Index: 811418 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1479960 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8902. Min Act: -0.0000

Data Index: 243203 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.9092. Min Act: -0.0000

Data Index: 562119 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1437899 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1079247 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8508. Min Act: -0.0000

Data Index: 742728 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.0819. Min Range: -1.0819

Max Act: 0.8196. Min Act: -0.0000

Data Index: 332644 (C4 (Web Text))

Max Activating Token Index: 693