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

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

Neuron 939 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: 5.7096. Min Range: -5.7096

Max Act: 5.7096. Min Act: -0.1700

Data Index: 182576 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.5221. Min Act: -0.1700

Data Index: 955957 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.5846. Min Act: -0.1700

Data Index: 632311 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4909. Min Act: -0.1700

Data Index: 932086 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.5221. Min Act: -0.1700

Data Index: 1275207 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4596. Min Act: -0.1700

Data Index: 799113 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4284. Min Act: -0.1700

Data Index: 6407 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4596. Min Act: -0.1700

Data Index: 1250500 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1699

Data Index: 77194 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 68837 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 817188 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 327361 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 1243319 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3034. Min Act: -0.1700

Data Index: 485347 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 1226116 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3659. Min Act: -0.1700

Data Index: 429243 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 713832 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 142916 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3659. Min Act: -0.1700

Data Index: 235025 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3659. Min Act: -0.1700

Data Index: 563598 (C4 (Web Text))

Max Activating Token Index: 691