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

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

Neuron 2020 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: 3.8791. Min Range: -3.8791

Max Act: 3.8791. Min Act: -0.1700

Data Index: 353192 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.8791. Min Act: -0.1700

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 567287 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 351169 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.8165. Min Act: -0.1700

Data Index: 86278 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.8165. Min Act: -0.1700

Data Index: 363985 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1005807 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1035873 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 53684 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 493936 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7226. Min Act: -0.1700

Data Index: 370465 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7852. Min Act: -0.1700

Data Index: 520380 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.8165. Min Act: -0.1700

Data Index: 257404 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 174258 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 3.8791. Min Range: -3.8791

Max Act: 3.7539. Min Act: -0.1700

Data Index: 264039 (C4 (Web Text))

Max Activating Token Index: 965