Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3527 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0284. Min Act: -0.0003

Data Index: 1068996 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.1020. Min Act: -0.0003

Data Index: 447480 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9086. Min Act: -0.0003

Data Index: 549988 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9601. Min Act: -0.0003

Data Index: 772335 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8550. Min Act: -0.0003

Data Index: 888162 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9803. Min Act: -0.0003

Data Index: 873809 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0293. Min Act: -0.0003

Data Index: 684105 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8478. Min Act: -0.0003

Data Index: 1178961 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9587. Min Act: -0.0003

Data Index: 1292941 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9062. Min Act: -0.0003

Data Index: 748329 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9059. Min Act: -0.0003

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9542. Min Act: -0.0003

Data Index: 655525 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8434. Min Act: -0.0003

Data Index: 860209 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9807. Min Act: -0.0003

Data Index: 1091743 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8607. Min Act: -0.0003

Data Index: 352097 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8849. Min Act: -0.0003

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8554. Min Act: -0.0003

Data Index: 51384 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9629. Min Act: -0.0003

Data Index: 127275 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9234. Min Act: -0.0003

Data Index: 1131335 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.7872. Min Act: -0.0003

Data Index: 1078961 (C4 (Web Text))

Max Activating Token Index: 841