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

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

Neuron 1696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.7396. Min Act: -0.1700

Data Index: 296074 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5830. Min Act: -0.1700

Data Index: 742835 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5204. Min Act: -0.1700

Data Index: 802427 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1012999 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5830. Min Act: -0.1700

Data Index: 1191669 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5517. Min Act: -0.1700

Data Index: 878355 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4891. Min Act: -0.1700

Data Index: 884732 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4891. Min Act: -0.1700

Data Index: 441979 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5204. Min Act: -0.1700

Data Index: 210450 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4577. Min Act: -0.1700

Data Index: 942957 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.5204. Min Act: -0.1700

Data Index: 668988 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4891. Min Act: -0.1700

Data Index: 275091 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4577. Min Act: -0.1700

Data Index: 1246013 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4577. Min Act: -0.1700

Data Index: 942652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4891. Min Act: -0.1700

Data Index: 686068 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4577. Min Act: -0.1700

Data Index: 770835 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4264. Min Act: -0.1700

Data Index: 372342 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4264. Min Act: -0.1700

Data Index: 872232 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.3636. Min Act: -0.1700

Data Index: 144745 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.7396. Min Range: -3.7396

Max Act: 3.4264. Min Act: -0.1700

Data Index: 379753 (C4 (Web Text))

Max Activating Token Index: 863