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

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

Neuron 1169 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.6504. Min Act: -0.1700

Data Index: 369214 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.6034. Min Act: -0.1700

Data Index: 324256 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5721. Min Act: -0.1700

Data Index: 420312 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.6034. Min Act: -0.1700

Data Index: 86715 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5721. Min Act: -0.1700

Data Index: 269809 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5721. Min Act: -0.1700

Data Index: 1053942 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.6191. Min Act: -0.1700

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5564. Min Act: -0.1700

Data Index: 1238287 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4938. Min Act: -0.1700

Data Index: 944925 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4938. Min Act: -0.1700

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4781. Min Act: -0.1700

Data Index: 34427 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5408. Min Act: -0.1700

Data Index: 898473 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5408. Min Act: -0.1700

Data Index: 361894 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4468. Min Act: -0.1700

Data Index: 1014693 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4781. Min Act: -0.1700

Data Index: 184148 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4938. Min Act: -0.1700

Data Index: 1068807 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4781. Min Act: -0.1700

Data Index: 85188 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4781. Min Act: -0.1700

Data Index: 250658 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4311. Min Act: -0.1700

Data Index: 1184002 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4624. Min Act: -0.1700

Data Index: 144444 (C4 (Web Text))

Max Activating Token Index: 172