Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6982. Min Act: -0.0002

Data Index: 680495 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6663. Min Act: -0.0002

Data Index: 448290 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6423. Min Act: -0.0002

Data Index: 937415 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6372. Min Act: -0.0002

Data Index: 618525 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5837. Min Act: -0.0002

Data Index: 770967 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6207. Min Act: -0.0002

Data Index: 471396 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6393. Min Act: -0.0002

Data Index: 318147 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6149. Min Act: -0.0002

Data Index: 571723 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6124. Min Act: -0.0002

Data Index: 1302064 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6060. Min Act: -0.0002

Data Index: 72655 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5869. Min Act: -0.0002

Data Index: 273510 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6020. Min Act: -0.0002

Data Index: 607728 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5920. Min Act: -0.0002

Data Index: 527362 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5860. Min Act: -0.0002

Data Index: 586332 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5689. Min Act: -0.0002

Data Index: 886786 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5899. Min Act: -0.0002

Data Index: 1169408 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5888. Min Act: -0.0002

Data Index: 58768 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5456. Min Act: -0.0002

Data Index: 1044374 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5447. Min Act: -0.0002

Data Index: 70089 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5620. Min Act: -0.0002

Data Index: 1219240 (C4 (Web Text))

Max Activating Token Index: 380