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

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

Neuron 1336 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: 3.7440. Min Range: -3.7440

Max Act: 3.7440. Min Act: -0.1700

Data Index: 633233 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.6188. Min Act: -0.1700

Data Index: 112227 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.5875. Min Act: -0.1700

Data Index: 1057989 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.6501. Min Act: -0.1700

Data Index: 138187 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.5875. Min Act: -0.1700

Data Index: 327747 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.5561. Min Act: -0.1700

Data Index: 545368 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4621. Min Act: -0.1700

Data Index: 146526 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.5248. Min Act: -0.1700

Data Index: 195034 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4935. Min Act: -0.1700

Data Index: 1094079 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4621. Min Act: -0.1700

Data Index: 760629 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4621. Min Act: -0.1700

Data Index: 1220279 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4308. Min Act: -0.1700

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4308. Min Act: -0.1700

Data Index: 708948 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.3994. Min Act: -0.1700

Data Index: 774546 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.3994. Min Act: -0.1700

Data Index: 248909 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4308. Min Act: -0.1700

Data Index: 50364 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.3994. Min Act: -0.1700

Data Index: 24775 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.3523. Min Act: -0.1700

Data Index: 110135 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1079 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 3.7440. Min Range: -3.7440

Max Act: 3.4308. Min Act: -0.1700

Data Index: 954010 (C4 (Web Text))

Max Activating Token Index: 299