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

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

Neuron 1894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2802. Min Act: -0.1700

Data Index: 1356049 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2488. Min Act: -0.1700

Data Index: 688734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2645. Min Act: -0.1700

Data Index: 198593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2016. Min Act: -0.1700

Data Index: 1096348 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2016. Min Act: -0.1700

Data Index: 464310 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2016. Min Act: -0.1700

Data Index: 69634 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1229. Min Act: -0.1700

Data Index: 40636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1387. Min Act: -0.1700

Data Index: 685052 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1544. Min Act: -0.1700

Data Index: 175902 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1071. Min Act: -0.1700

Data Index: 790600 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1071. Min Act: -0.1700

Data Index: 611141 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1071. Min Act: -0.1700

Data Index: 601599 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1071. Min Act: -0.1700

Data Index: 1241927 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0914. Min Act: -0.1700

Data Index: 1346416 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1063993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0440. Min Act: -0.1700

Data Index: 625579 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0282. Min Act: -0.1700

Data Index: 984126 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0124. Min Act: -0.1700

Data Index: 210618 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0440. Min Act: -0.1700

Data Index: 549647 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0440. Min Act: -0.1700

Data Index: 962695 (C4 (Web Text))

Max Activating Token Index: 281