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

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

Neuron 1972 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: 3.2372. Min Range: -3.2372

Max Act: 3.2372. Min Act: -0.1700

Data Index: 97776 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2372. Min Act: -0.1700

Data Index: 217370 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2215. Min Act: -0.1700

Data Index: 70841 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2372. Min Act: -0.1700

Data Index: 735781 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2058. Min Act: -0.1700

Data Index: 1015881 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2058. Min Act: -0.1700

Data Index: 219016 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1049241 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1743. Min Act: -0.1700

Data Index: 145424 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1585. Min Act: -0.1700

Data Index: 382375 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1585. Min Act: -0.1700

Data Index: 405059 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1585. Min Act: -0.1700

Data Index: 811666 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1428. Min Act: -0.1700

Data Index: 386029 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1585. Min Act: -0.1700

Data Index: 235327 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1428. Min Act: -0.1700

Data Index: 184822 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1428. Min Act: -0.1700

Data Index: 368110 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1428. Min Act: -0.1700

Data Index: 224774 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.1270. Min Act: -0.1700

Data Index: 201601 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.0955. Min Act: -0.1700

Data Index: 1026993 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.0955. Min Act: -0.1700

Data Index: 919205 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.0955. Min Act: -0.1700

Data Index: 517820 (C4 (Web Text))

Max Activating Token Index: 505