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

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

Neuron 459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.3932. Min Act: -0.1700

Data Index: 324509 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1114467 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1142232 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2676. Min Act: -0.1700

Data Index: 36876 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2047. Min Act: -0.1700

Data Index: 1103506 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1890. Min Act: -0.1700

Data Index: 608783 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1268235 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2204. Min Act: -0.1700

Data Index: 283432 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1173076 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1890. Min Act: -0.1700

Data Index: 690852 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1296101 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.2204. Min Act: -0.1700

Data Index: 1317012 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1890. Min Act: -0.1700

Data Index: 319743 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1732. Min Act: -0.1700

Data Index: 560376 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1575. Min Act: -0.1700

Data Index: 105932 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1575. Min Act: -0.1700

Data Index: 435552 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1732. Min Act: -0.1700

Data Index: 128406 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1260. Min Act: -0.1700

Data Index: 255682 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1417. Min Act: -0.1700

Data Index: 294159 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.3932. Min Range: -3.3932

Max Act: 3.1260. Min Act: -0.1700

Data Index: 983763 (C4 (Web Text))

Max Activating Token Index: 416