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

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

Neuron 16 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: 3.7152. Min Range: -3.7152

Max Act: 3.7152. Min Act: -0.1700

Data Index: 974621 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1141800 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6526. Min Act: -0.1700

Data Index: 139583 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6526. Min Act: -0.1700

Data Index: 576911 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1224850 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6526. Min Act: -0.1700

Data Index: 91721 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6213. Min Act: -0.1700

Data Index: 392959 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1251308 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1089137 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 825045 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5587. Min Act: -0.1700

Data Index: 707820 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1037369 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 237041 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 35233 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1350073 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1312896 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1199513 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5587. Min Act: -0.1700

Data Index: 94373 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5587. Min Act: -0.1700

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5587. Min Act: -0.1700

Data Index: 678154 (C4 (Web Text))

Max Activating Token Index: 799