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

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

Neuron 1266 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.8414. Min Act: -0.1700

Data Index: 699475 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.6067. Min Act: -0.1700

Data Index: 640025 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.5597. Min Act: -0.1700

Data Index: 443839 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.5127. Min Act: -0.1700

Data Index: 263317 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.5284. Min Act: -0.1700

Data Index: 465618 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.5127. Min Act: -0.1700

Data Index: 1128651 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4657. Min Act: -0.1700

Data Index: 457701 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4500. Min Act: -0.1700

Data Index: 706123 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4187. Min Act: -0.1700

Data Index: 5728 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4030. Min Act: -0.1700

Data Index: 32204 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4187. Min Act: -0.1700

Data Index: 73597 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.4030. Min Act: -0.1700

Data Index: 247479 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3716. Min Act: -0.1700

Data Index: 682543 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3873. Min Act: -0.1700

Data Index: 786883 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3873. Min Act: -0.1700

Data Index: 1069300 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3716. Min Act: -0.1700

Data Index: 763824 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3716. Min Act: -0.1700

Data Index: 1231202 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3559. Min Act: -0.1700

Data Index: 605754 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3559. Min Act: -0.1700

Data Index: 442769 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.8414. Min Range: -3.8414

Max Act: 3.3402. Min Act: -0.1700

Data Index: 89576 (C4 (Web Text))

Max Activating Token Index: 913