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

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

Neuron 1598 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1266. Min Range: -3.1266

Max Act: 3.0417. Min Act: -0.0001

Data Index: 735291 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 3.1266. Min Range: -3.1266

Max Act: 3.1266. Min Act: -0.0001

Data Index: 782933 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.1266. Min Range: -3.1266

Max Act: 3.0112. Min Act: -0.0001

Data Index: 1253545 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.1266. Min Range: -3.1266

Max Act: 3.0335. Min Act: -0.0001

Data Index: 222664 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7794. Min Act: -0.0001

Data Index: 874840 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7696. Min Act: -0.0001

Data Index: 421556 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7340. Min Act: -0.0001

Data Index: 613119 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6037. Min Act: -0.0001

Data Index: 1005569 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.9525. Min Act: -0.0001

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.8905. Min Act: -0.0001

Data Index: 113023 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7424. Min Act: -0.0001

Data Index: 1263362 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5169. Min Act: -0.0001

Data Index: 356248 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5138. Min Act: -0.0001

Data Index: 455862 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6080. Min Act: -0.0001

Data Index: 150397 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5738. Min Act: -0.0001

Data Index: 1279476 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.8497. Min Act: -0.0001

Data Index: 68041 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6785. Min Act: -0.0001

Data Index: 730638 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6230. Min Act: -0.0001

Data Index: 1171456 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7503. Min Act: -0.0001

Data Index: 17240 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.4777. Min Act: -0.0001

Data Index: 1248920 (C4 (Web Text))

Max Activating Token Index: 397