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

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

Neuron 1260 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.5152. Min Act: -0.1700

Data Index: 373494 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4839. Min Act: -0.1700

Data Index: 362811 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4996. Min Act: -0.1700

Data Index: 650877 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4369. Min Act: -0.1700

Data Index: 117183 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4369. Min Act: -0.1700

Data Index: 142518 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4212. Min Act: -0.1700

Data Index: 291037 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4212. Min Act: -0.1700

Data Index: 871301 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4369. Min Act: -0.1700

Data Index: 778555 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4369. Min Act: -0.1700

Data Index: 744237 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4212. Min Act: -0.1700

Data Index: 680565 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4369. Min Act: -0.1700

Data Index: 448533 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.4055. Min Act: -0.1700

Data Index: 811698 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3427. Min Act: -0.1700

Data Index: 175768 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3584. Min Act: -0.1699

Data Index: 690631 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3741. Min Act: -0.1700

Data Index: 410152 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1105590 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3898. Min Act: -0.1700

Data Index: 374856 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3427. Min Act: -0.1700

Data Index: 205834 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3898. Min Act: -0.1700

Data Index: 1169729 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.5152. Min Range: -3.5152

Max Act: 3.3741. Min Act: -0.1700

Data Index: 381733 (C4 (Web Text))

Max Activating Token Index: 222