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

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

Neuron 1635 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: 5.8533. Min Range: -5.8533

Max Act: 5.8533. Min Act: -0.1700

Data Index: 1040362 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.6971. Min Act: -0.1700

Data Index: 1088027 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.7283. Min Act: -0.1700

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.6971. Min Act: -0.1700

Data Index: 783137 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.5721. Min Act: -0.1700

Data Index: 12381 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.4471. Min Act: -0.1700

Data Index: 1104260 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3533. Min Act: -0.1700

Data Index: 1330661 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.4158. Min Act: -0.1700

Data Index: 795672 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3846. Min Act: -0.1700

Data Index: 210791 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.4471. Min Act: -0.1700

Data Index: 112667 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3846. Min Act: -0.1700

Data Index: 1011189 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3846. Min Act: -0.1700

Data Index: 303686 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3221. Min Act: -0.1700

Data Index: 1300104 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.2908. Min Act: -0.1700

Data Index: 141555 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.3221. Min Act: -0.1700

Data Index: 1179022 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.2908. Min Act: -0.1700

Data Index: 490624 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.2596. Min Act: -0.1700

Data Index: 321554 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.2596. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.2908. Min Act: -0.1700

Data Index: 949185 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 5.8533. Min Range: -5.8533

Max Act: 5.1971. Min Act: -0.1700

Data Index: 221272 (C4 (Web Text))

Max Activating Token Index: 705