Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 169 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0679. Min Act: -0.1700

Data Index: 477254 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0679. Min Act: -0.1700

Data Index: 571963 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0679. Min Act: -0.1700

Data Index: 1015233 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0679. Min Act: -0.1700

Data Index: 1168423 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0521. Min Act: -0.1700

Data Index: 972346 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0679. Min Act: -0.1700

Data Index: 1028505 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 1127692 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0363. Min Act: -0.1700

Data Index: 12950 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 1269758 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0521. Min Act: -0.1700

Data Index: 758732 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0363. Min Act: -0.1700

Data Index: 383027 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 786624 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 109227 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 894123 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0047. Min Act: -0.1700

Data Index: 835369 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0363. Min Act: -0.1700

Data Index: 1345251 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0205. Min Act: -0.1700

Data Index: 1150244 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 3.0679. Min Range: -3.0679

Max Act: 3.0047. Min Act: -0.1700

Data Index: 860659 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.0679. Min Range: -3.0679

Max Act: 2.9889. Min Act: -0.1700

Data Index: 1100544 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.0679. Min Range: -3.0679

Max Act: 2.9889. Min Act: -0.1700

Data Index: 615833 (C4 (Web Text))

Max Activating Token Index: 8