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

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

Neuron 1649 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: 7.3984. Min Range: -7.3984

Max Act: 7.3984. Min Act: -0.1700

Data Index: 372761 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.9921. Min Act: -0.1700

Data Index: 338427 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.9609. Min Act: -0.1700

Data Index: 1553041 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.7421. Min Act: -0.1700

Data Index: 542289 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.7421. Min Act: -0.1700

Data Index: 1349995 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6484. Min Act: -0.1700

Data Index: 111957 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6796. Min Act: -0.1700

Data Index: 560706 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.7109. Min Act: -0.1700

Data Index: 1635594 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6171. Min Act: -0.1700

Data Index: 642290 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6796. Min Act: -0.1700

Data Index: 901428 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.5546. Min Act: -0.1700

Data Index: 432762 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6171. Min Act: -0.1700

Data Index: 21434 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.5859. Min Act: -0.1700

Data Index: 793492 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.4921. Min Act: -0.1700

Data Index: 1241390 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.5234. Min Act: -0.1700

Data Index: 230839 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.6171. Min Act: -0.1700

Data Index: 257698 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.5859. Min Act: -0.1700

Data Index: 892907 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.4921. Min Act: -0.1700

Data Index: 1164690 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.4921. Min Act: -0.1700

Data Index: 233106 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 7.3984. Min Range: -7.3984

Max Act: 6.4609. Min Act: -0.1700

Data Index: 1075320 (C4 (Web Text))

Max Activating Token Index: 593