Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 61 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1948. Min Act: -0.1700

Data Index: 578089 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1010. Min Act: -0.1700

Data Index: 498076 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9448. Min Act: -0.1700

Data Index: 1096558 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.8823. Min Act: -0.1700

Data Index: 1007773 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.8510. Min Act: -0.1700

Data Index: 398949 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.8823. Min Act: -0.1700

Data Index: 430410 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.8198. Min Act: -0.1700

Data Index: 886829 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.8198. Min Act: -0.1700

Data Index: 274748 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7885. Min Act: -0.1700

Data Index: 1351514 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7260. Min Act: -0.1700

Data Index: 1047699 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7573. Min Act: -0.1700

Data Index: 1210297 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7260. Min Act: -0.1700

Data Index: 534974 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7260. Min Act: -0.1700

Data Index: 821985 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7573. Min Act: -0.1700

Data Index: 753927 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.7260. Min Act: -0.1700

Data Index: 206955 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.6948. Min Act: -0.1700

Data Index: 1278169 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.6948. Min Act: -0.1700

Data Index: 832903 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.6635. Min Act: -0.1700

Data Index: 1032665 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.6948. Min Act: -0.1700

Data Index: 432927 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.6635. Min Act: -0.1700

Data Index: 925763 (C4 (Web Text))

Max Activating Token Index: 689