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

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

Neuron 1984 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: 7.3707. Min Range: -7.3707

Max Act: 7.3394. Min Act: -0.1700

Data Index: 303160 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.3707. Min Act: -0.1700

Data Index: 1313018 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.2144. Min Act: -0.1700

Data Index: 139773 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.2144. Min Act: -0.1700

Data Index: 336241 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.2769. Min Act: -0.1700

Data Index: 464644 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.2457. Min Act: -0.1699

Data Index: 597259 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1832. Min Act: -0.1700

Data Index: 509285 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1207. Min Act: -0.1700

Data Index: 424160 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.2144. Min Act: -0.1700

Data Index: 185474 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1207. Min Act: -0.1700

Data Index: 758446 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1832. Min Act: -0.1700

Data Index: 77450 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1832. Min Act: -0.1700

Data Index: 262636 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.0894. Min Act: -0.1700

Data Index: 92643 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1207. Min Act: -0.1700

Data Index: 576601 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1832. Min Act: -0.1700

Data Index: 608219 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1519. Min Act: -0.1700

Data Index: 726438 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1207. Min Act: -0.1700

Data Index: 1012629 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.1207. Min Act: -0.1700

Data Index: 499636 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.0894. Min Act: -0.1700

Data Index: 744479 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 7.3707. Min Range: -7.3707

Max Act: 7.0894. Min Act: -0.1700

Data Index: 972302 (C4 (Web Text))

Max Activating Token Index: 57