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

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

Neuron 526 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.6104. Min Act: -0.1699

Data Index: 259478 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.5714. Min Act: -0.1699

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4385. Min Act: -0.1699

Data Index: 293154 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4620. Min Act: -0.1699

Data Index: 809500 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.5010. Min Act: -0.1699

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4698. Min Act: -0.1699

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4932. Min Act: -0.1699

Data Index: 265877 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4073. Min Act: -0.1699

Data Index: 498993 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.5167. Min Act: -0.1699

Data Index: 930014 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.5010. Min Act: -0.1699

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3370. Min Act: -0.1699

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.2589. Min Act: -0.1699

Data Index: 253120 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.2979. Min Act: -0.1699

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3135. Min Act: -0.1699

Data Index: 740418 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3526. Min Act: -0.1699

Data Index: 882203 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3839. Min Act: -0.1699

Data Index: 360567 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3760. Min Act: -0.1699

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4620. Min Act: -0.1699

Data Index: 290068 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.3526. Min Act: -0.1699

Data Index: 886938 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 5.6104. Min Range: -5.6104

Max Act: 5.4151. Min Act: -0.1699

Data Index: 1033251 (C4 (Web Text))

Max Activating Token Index: 742