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

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

Neuron 333 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: 3.6998. Min Range: -3.6998

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1274990 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6998. Min Act: -0.1700

Data Index: 808156 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6685. Min Act: -0.1700

Data Index: 332737 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6372. Min Act: -0.1700

Data Index: 268805 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6059. Min Act: -0.1700

Data Index: 947705 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6059. Min Act: -0.1700

Data Index: 672722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6372. Min Act: -0.1700

Data Index: 240730 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6059. Min Act: -0.1700

Data Index: 1297050 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1343093 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5746. Min Act: -0.1700

Data Index: 446497 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5432. Min Act: -0.1700

Data Index: 590070 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5746. Min Act: -0.1700

Data Index: 485458 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5746. Min Act: -0.1700

Data Index: 499607 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.6059. Min Act: -0.1700

Data Index: 702210 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5119. Min Act: -0.1700

Data Index: 562372 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5432. Min Act: -0.1700

Data Index: 431778 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5432. Min Act: -0.1700

Data Index: 562460 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5432. Min Act: -0.1700

Data Index: 330216 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5432. Min Act: -0.1700

Data Index: 563724 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 3.6998. Min Range: -3.6998

Max Act: 3.5119. Min Act: -0.1700

Data Index: 690605 (C4 (Web Text))

Max Activating Token Index: 196