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

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

Neuron 3725 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: 2.0144. Min Range: -2.0144

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1129843 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.8683. Min Act: -0.0000

Data Index: 619613 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3640. Min Act: -0.0000

Data Index: 636379 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3777. Min Act: -0.0000

Data Index: 803492 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1206309 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1182614 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9853. Min Act: -0.0000

Data Index: 98863 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1139817 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8932. Min Act: -0.0000

Data Index: 252109 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9831. Min Act: -0.0000

Data Index: 944249 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9243. Min Act: -0.0000

Data Index: 280977 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9435. Min Act: -0.0000

Data Index: 547178 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1210172 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8562. Min Act: -0.0000

Data Index: 35105 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8813. Min Act: -0.0000

Data Index: 755506 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.9069. Min Act: -0.0000

Data Index: 784400 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1246126 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8548. Min Act: -0.0000

Data Index: 310685 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8297. Min Act: -0.0000

Data Index: 405277 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 2.0144. Min Range: -2.0144

Max Act: 0.8201. Min Act: -0.0000

Data Index: 662694 (C4 (Web Text))

Max Activating Token Index: 70