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

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

Neuron 1144 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: 5.3934. Min Range: -5.3934

Max Act: 5.3934. Min Act: -0.1700

Data Index: 710392 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 5.3934. Min Range: -5.3934

Max Act: 5.3621. Min Act: -0.1696

Data Index: 77048 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.9871. Min Act: -0.1700

Data Index: 805085 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.9246. Min Act: -0.1700

Data Index: 760771 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.8934. Min Act: -0.1700

Data Index: 433185 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.8621. Min Act: -0.1700

Data Index: 826829 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7684. Min Act: -0.1700

Data Index: 1023504 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7059. Min Act: -0.1700

Data Index: 1232853 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7684. Min Act: -0.1700

Data Index: 806966 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7684. Min Act: -0.1700

Data Index: 844704 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7059. Min Act: -0.1700

Data Index: 635912 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7059. Min Act: -0.1700

Data Index: 407685 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7371. Min Act: -0.1699

Data Index: 1095874 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.7059. Min Act: -0.1700

Data Index: 425142 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1699

Data Index: 1083068 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1667

Data Index: 825589 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1700

Data Index: 1247231 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1700

Data Index: 780089 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1700

Data Index: 1072058 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 5.3934. Min Range: -5.3934

Max Act: 4.6746. Min Act: -0.1700

Data Index: 998231 (C4 (Web Text))

Max Activating Token Index: 368