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

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

Neuron 4318 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1011887 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1409731 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.7056. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1368339 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6021. Min Act: -0.0000

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1377613 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1529228 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1421797 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1419437 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1447369 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1546133 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1534994 (Python Code)

Max Activating Token Index: 280

Text #12

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1387059 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1509350 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1376173 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5550. Min Act: -0.0000

Data Index: 866648 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1546615 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5213. Min Act: -0.0000

Data Index: 552491 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1635095 (Python Code)

Max Activating Token Index: 165

Text #19

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.4475. Min Act: -0.0000

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 518