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

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

Neuron 1672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.3233. Min Act: -0.1700

Data Index: 636161 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1035570 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1116228 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1976. Min Act: -0.1700

Data Index: 4396 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1316963 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1661. Min Act: -0.1700

Data Index: 821301 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1661. Min Act: -0.1700

Data Index: 321780 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1661. Min Act: -0.1700

Data Index: 635685 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1504. Min Act: -0.1700

Data Index: 601943 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1189. Min Act: -0.1700

Data Index: 465645 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1031. Min Act: -0.1700

Data Index: 840022 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0874. Min Act: -0.1700

Data Index: 157675 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0874. Min Act: -0.1700

Data Index: 628344 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.1031. Min Act: -0.1700

Data Index: 214353 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0874. Min Act: -0.1700

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0558. Min Act: -0.1700

Data Index: 135408 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0558. Min Act: -0.1700

Data Index: 1241197 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0558. Min Act: -0.1700

Data Index: 992881 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0242. Min Act: -0.1700

Data Index: 971527 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 3.3233. Min Range: -3.3233

Max Act: 3.0084. Min Act: -0.1700

Data Index: 84813 (C4 (Web Text))

Max Activating Token Index: 106