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

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

Neuron 524 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: 3.8128. Min Range: -3.8128

Max Act: 3.7815. Min Act: -0.1700

Data Index: 1024469 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 128025 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7815. Min Act: -0.1700

Data Index: 1291528 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7815. Min Act: -0.1700

Data Index: 1118903 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 800370 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 472525 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 647773 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.8128. Min Act: -0.1700

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7815. Min Act: -0.1700

Data Index: 859983 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 354534 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7503. Min Act: -0.1700

Data Index: 360788 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7190. Min Act: -0.1700

Data Index: 1089078 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7659. Min Act: -0.1700

Data Index: 848177 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7659. Min Act: -0.1700

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7346. Min Act: -0.1700

Data Index: 827132 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7346. Min Act: -0.1700

Data Index: 344048 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7346. Min Act: -0.1700

Data Index: 1132296 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7972. Min Act: -0.1700

Data Index: 491550 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.7659. Min Act: -0.1700

Data Index: 632382 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.8128. Min Range: -3.8128

Max Act: 3.6877. Min Act: -0.1700

Data Index: 732306 (C4 (Web Text))

Max Activating Token Index: 578