Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1106 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1238654 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.6766. Min Act: -0.1700

Data Index: 1144072 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1079895 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.6609. Min Act: -0.1700

Data Index: 675238 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1135770 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.5670. Min Act: -0.1700

Data Index: 39662 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.5670. Min Act: -0.1700

Data Index: 457669 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.5513. Min Act: -0.1700

Data Index: 390312 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.5200. Min Act: -0.1700

Data Index: 1256287 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.5200. Min Act: -0.1700

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4730. Min Act: -0.1700

Data Index: 851091 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4573. Min Act: -0.1700

Data Index: 738869 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4730. Min Act: -0.1700

Data Index: 220280 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4730. Min Act: -0.1700

Data Index: 455961 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4887. Min Act: -0.1700

Data Index: 912001 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4573. Min Act: -0.1700

Data Index: 1011204 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4573. Min Act: -0.1700

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4417. Min Act: -0.1700

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 3.7235. Min Range: -3.7235

Max Act: 3.4573. Min Act: -0.1700

Data Index: 832424 (C4 (Web Text))

Max Activating Token Index: 79