Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 143 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.5426. Min Act: -0.1700

Data Index: 23874 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.4488. Min Act: -0.1700

Data Index: 429234 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.4801. Min Act: -0.1700

Data Index: 1349398 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.2613. Min Act: -0.1700

Data Index: 824539 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1988. Min Act: -0.1700

Data Index: 1099719 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1988. Min Act: -0.1700

Data Index: 293844 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.2301. Min Act: -0.1700

Data Index: 104986 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1676. Min Act: -0.1700

Data Index: 767382 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1051. Min Act: -0.1700

Data Index: 421289 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 706240 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1051. Min Act: -0.1700

Data Index: 1149661 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1051. Min Act: -0.1700

Data Index: 1009423 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 1045401 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1051. Min Act: -0.1700

Data Index: 413993 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 487814 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 1033364 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.1363. Min Act: -0.1700

Data Index: 872797 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 1129898 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 1008770 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 5.5426. Min Range: -5.5426

Max Act: 5.0738. Min Act: -0.1700

Data Index: 1210888 (C4 (Web Text))

Max Activating Token Index: 961