Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1248 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4629. Min Act: -0.1700

Data Index: 744425 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.6191. Min Act: -0.1700

Data Index: 1051332 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4629. Min Act: -0.1700

Data Index: 148736 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4629. Min Act: -0.1700

Data Index: 208806 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.5254. Min Act: -0.1700

Data Index: 356673 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4941. Min Act: -0.1700

Data Index: 36991 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4316. Min Act: -0.1700

Data Index: 106997 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4004. Min Act: -0.1700

Data Index: 986038 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.4316. Min Act: -0.1700

Data Index: 288162 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.3691. Min Act: -0.1700

Data Index: 402610 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.3066. Min Act: -0.1700

Data Index: 94818 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2441. Min Act: -0.1700

Data Index: 734447 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.3691. Min Act: -0.1700

Data Index: 942037 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2754. Min Act: -0.1700

Data Index: 154469 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2754. Min Act: -0.1700

Data Index: 1123006 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2754. Min Act: -0.1700

Data Index: 758023 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2441. Min Act: -0.1700

Data Index: 714961 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2754. Min Act: -0.1700

Data Index: 1134764 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2754. Min Act: -0.1700

Data Index: 594430 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 5.6191. Min Range: -5.6191

Max Act: 5.2441. Min Act: -0.1700

Data Index: 482114 (C4 (Web Text))

Max Activating Token Index: 570