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

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

Neuron 3708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.9214. Min Act: -0.0000

Data Index: 1080271 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1187580 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.5894. Min Act: -0.0000

Data Index: 727577 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3802. Min Act: -0.0000

Data Index: 1320142 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.2674. Min Act: -0.0000

Data Index: 175250 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.2827. Min Act: -0.0000

Data Index: 1241550 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3111. Min Act: -0.0000

Data Index: 71159 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9183. Min Act: -0.0000

Data Index: 857078 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.0050. Min Act: -0.0000

Data Index: 492158 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9781. Min Act: -0.0000

Data Index: 361126 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9406. Min Act: -0.0000

Data Index: 274381 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.0314. Min Act: -0.0000

Data Index: 195867 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.1007. Min Act: -0.0000

Data Index: 385856 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.0814. Min Act: -0.0000

Data Index: 340158 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9082. Min Act: -0.0000

Data Index: 201804 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.8341. Min Act: -0.0000

Data Index: 507865 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.9289. Min Act: -0.0000

Data Index: 1018363 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.8095. Min Act: -0.0000

Data Index: 551506 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 2.9214. Min Range: -2.9214

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1703 (C4 (Web Text))

Max Activating Token Index: 421