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

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

Neuron 1718 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: 5.9946. Min Range: -5.9946

Max Act: 5.9946. Min Act: -0.1695

Data Index: 1182696 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.9634. Min Act: -0.1700

Data Index: 728020 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.8071. Min Act: -0.1700

Data Index: 406303 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.8071. Min Act: -0.1700

Data Index: 834399 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.7134. Min Act: -0.1700

Data Index: 916881 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.7446. Min Act: -0.1700

Data Index: 806596 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.7134. Min Act: -0.1700

Data Index: 41633 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6821. Min Act: -0.1700

Data Index: 1349165 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.7446. Min Act: -0.1700

Data Index: 817269 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6821. Min Act: -0.1700

Data Index: 1244177 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6509. Min Act: -0.1700

Data Index: 1071868 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6509. Min Act: -0.1700

Data Index: 1215069 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.5571. Min Act: -0.1700

Data Index: 791701 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6509. Min Act: -0.1700

Data Index: 697410 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.5884. Min Act: -0.1700

Data Index: 39520 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6509. Min Act: -0.1691

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.5884. Min Act: -0.1700

Data Index: 79182 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6196. Min Act: -0.1700

Data Index: 961179 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.6196. Min Act: -0.1700

Data Index: 243564 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 5.9946. Min Range: -5.9946

Max Act: 5.5884. Min Act: -0.1699

Data Index: 72536 (C4 (Web Text))

Max Activating Token Index: 927