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

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

Neuron 3311 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: 0.7030. Min Range: -0.7030

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1330975 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5995. Min Act: -0.0000

Data Index: 12488 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1028274 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5898. Min Act: -0.0000

Data Index: 179657 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5322. Min Act: -0.0000

Data Index: 553575 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1236089 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1286644 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5432. Min Act: -0.0000

Data Index: 901754 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1287992 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5072. Min Act: -0.0000

Data Index: 818867 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5381. Min Act: -0.0000

Data Index: 494497 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5286. Min Act: -0.0000

Data Index: 548964 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5349. Min Act: -0.0000

Data Index: 478400 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5251. Min Act: -0.0000

Data Index: 774937 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5060. Min Act: -0.0000

Data Index: 593291 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5344. Min Act: -0.0000

Data Index: 236584 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4977. Min Act: -0.0000

Data Index: 233721 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4919. Min Act: -0.0000

Data Index: 128200 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4825. Min Act: -0.0000

Data Index: 699384 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5131. Min Act: -0.0000

Data Index: 383004 (C4 (Web Text))

Max Activating Token Index: 11