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

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

Neuron 555 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8733. Min Act: -0.0002

Data Index: 371281 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7650. Min Act: -0.0002

Data Index: 611820 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7578. Min Act: -0.0002

Data Index: 119243 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7505. Min Act: -0.0003

Data Index: 267589 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7492. Min Act: -0.0002

Data Index: 731758 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7327. Min Act: -0.0003

Data Index: 539950 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7328. Min Act: -0.0002

Data Index: 1124362 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7416. Min Act: -0.0002

Data Index: 494762 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7148. Min Act: -0.0002

Data Index: 1331193 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7250. Min Act: -0.0002

Data Index: 541361 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7248. Min Act: -0.0002

Data Index: 614477 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7252. Min Act: -0.0002

Data Index: 161875 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7245. Min Act: -0.0002

Data Index: 1182406 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7315. Min Act: -0.0002

Data Index: 25029 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7126. Min Act: -0.0003

Data Index: 1000902 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7161. Min Act: -0.0002

Data Index: 414975 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7210. Min Act: -0.0002

Data Index: 1014380 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7094. Min Act: -0.0003

Data Index: 901618 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6973. Min Act: -0.0002

Data Index: 831423 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7077. Min Act: -0.0002

Data Index: 1264084 (C4 (Web Text))

Max Activating Token Index: 762