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

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

Neuron 1824 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: 5.7709. Min Range: -5.7709

Max Act: 5.7396. Min Act: -0.1700

Data Index: 522150 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.7709. Min Act: -0.1700

Data Index: 50173 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.6146. Min Act: -0.1700

Data Index: 1273564 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.6771. Min Act: -0.1700

Data Index: 1078075 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.6771. Min Act: -0.1700

Data Index: 38784 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 347472 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5521. Min Act: -0.1700

Data Index: 1015384 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 1276757 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 247433 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 542063 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5521. Min Act: -0.1700

Data Index: 296128 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 941949 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5834. Min Act: -0.1700

Data Index: 873399 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5521. Min Act: -0.1700

Data Index: 450446 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5521. Min Act: -0.1700

Data Index: 1346615 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.6146. Min Act: -0.1700

Data Index: 1069814 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5521. Min Act: -0.1700

Data Index: 694827 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.4896. Min Act: -0.1700

Data Index: 1092023 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.5209. Min Act: -0.1700

Data Index: 637113 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 5.7709. Min Range: -5.7709

Max Act: 5.4896. Min Act: -0.1700

Data Index: 1147473 (C4 (Web Text))

Max Activating Token Index: 964