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

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

Neuron 1572 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3946. Min Act: -0.1700

Data Index: 983708 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3161. Min Act: -0.1700

Data Index: 793082 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3161. Min Act: -0.1700

Data Index: 1182833 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3004. Min Act: -0.1700

Data Index: 152495 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3004. Min Act: -0.1700

Data Index: 702149 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3004. Min Act: -0.1700

Data Index: 782647 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.3004. Min Act: -0.1700

Data Index: 1306068 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2847. Min Act: -0.1700

Data Index: 25147 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 774756 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 971491 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 516938 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2533. Min Act: -0.1700

Data Index: 551945 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 84104 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2533. Min Act: -0.1700

Data Index: 355668 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2376. Min Act: -0.1700

Data Index: 3585 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 166014 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2690. Min Act: -0.1700

Data Index: 963143 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2533. Min Act: -0.1700

Data Index: 942392 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2376. Min Act: -0.1700

Data Index: 878363 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 3.3946. Min Range: -3.3946

Max Act: 3.2533. Min Act: -0.1700

Data Index: 827105 (C4 (Web Text))

Max Activating Token Index: 355