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

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

Neuron 1706 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: 3.9681. Min Range: -3.9681

Max Act: 3.9681. Min Act: -0.1700

Data Index: 11961 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.7805. Min Act: -0.1700

Data Index: 714812 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.7961. Min Act: -0.1700

Data Index: 766168 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.7335. Min Act: -0.1700

Data Index: 1011846 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.7022. Min Act: -0.1700

Data Index: 501621 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6866. Min Act: -0.1700

Data Index: 29986 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6866. Min Act: -0.1700

Data Index: 445016 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6866. Min Act: -0.1700

Data Index: 823137 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1190323 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1028357 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5927. Min Act: -0.1700

Data Index: 1038747 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6240. Min Act: -0.1700

Data Index: 106219 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.6083. Min Act: -0.1700

Data Index: 133204 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5927. Min Act: -0.1700

Data Index: 112180 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5613. Min Act: -0.1700

Data Index: 535787 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5770. Min Act: -0.1700

Data Index: 126 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5613. Min Act: -0.1700

Data Index: 67183 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5457. Min Act: -0.1700

Data Index: 185080 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5770. Min Act: -0.1700

Data Index: 802935 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.9681. Min Range: -3.9681

Max Act: 3.5144. Min Act: -0.1700

Data Index: 89367 (C4 (Web Text))

Max Activating Token Index: 202