Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1556 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.9144. Min Act: -0.1700

Data Index: 1250351 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7893. Min Act: -0.1700

Data Index: 984071 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7893. Min Act: -0.1700

Data Index: 1291312 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7893. Min Act: -0.1700

Data Index: 935013 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7893. Min Act: -0.1700

Data Index: 245988 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7267. Min Act: -0.1700

Data Index: 120876 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7267. Min Act: -0.1700

Data Index: 168118 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.7580. Min Act: -0.1700

Data Index: 1160947 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6328. Min Act: -0.1700

Data Index: 246434 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6954. Min Act: -0.1700

Data Index: 210405 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6641. Min Act: -0.1700

Data Index: 813013 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6328. Min Act: -0.1700

Data Index: 950124 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.5702. Min Act: -0.1700

Data Index: 715045 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6954. Min Act: -0.1700

Data Index: 1628455 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6641. Min Act: -0.1698

Data Index: 868170 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6328. Min Act: -0.1700

Data Index: 515405 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.5702. Min Act: -0.1700

Data Index: 404913 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.5702. Min Act: -0.1700

Data Index: 617909 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6328. Min Act: -0.1700

Data Index: 48878 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 3.9144. Min Range: -3.9144

Max Act: 3.6954. Min Act: -0.1700

Data Index: 684045 (C4 (Web Text))

Max Activating Token Index: 282