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

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

Neuron 572 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: 3.6974. Min Range: -3.6974

Max Act: 3.6974. Min Act: -0.1700

Data Index: 63945 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6817. Min Act: -0.1700

Data Index: 25366 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6817. Min Act: -0.1700

Data Index: 268729 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6504. Min Act: -0.1700

Data Index: 135940 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6191. Min Act: -0.1700

Data Index: 510821 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6191. Min Act: -0.1700

Data Index: 1190765 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6191. Min Act: -0.1700

Data Index: 1055326 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6035. Min Act: -0.1700

Data Index: 219166 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6191. Min Act: -0.1700

Data Index: 633201 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6035. Min Act: -0.1700

Data Index: 988773 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6035. Min Act: -0.1700

Data Index: 1247609 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 1140647 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 1053971 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 520132 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 461757 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 832484 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5721. Min Act: -0.1700

Data Index: 1277065 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 368358 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5878. Min Act: -0.1700

Data Index: 43556 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5721. Min Act: -0.1700

Data Index: 743063 (C4 (Web Text))

Max Activating Token Index: 619