Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2236. Min Range: -5.2236

Max Act: 5.2236. Min Act: -0.1700

Data Index: 7868 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 5.2236. Min Range: -5.2236

Max Act: 5.0048. Min Act: -0.1700

Data Index: 472313 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 5.2236. Min Range: -5.2236

Max Act: 5.0048. Min Act: -0.1700

Data Index: 1181073 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 5.2236. Min Range: -5.2236

Max Act: 5.0048. Min Act: -0.1700

Data Index: 234431 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9736. Min Act: -0.1700

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9579. Min Act: -0.1700

Data Index: 1444163 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9736. Min Act: -0.1700

Data Index: 535698 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9267. Min Act: -0.1700

Data Index: 1028998 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9267. Min Act: -0.1700

Data Index: 1055482 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8798. Min Act: -0.1700

Data Index: 1276927 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8954. Min Act: -0.1700

Data Index: 485723 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.9111. Min Act: -0.1700

Data Index: 1002367 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8642. Min Act: -0.1700

Data Index: 1081478 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8798. Min Act: -0.1700

Data Index: 1333046 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8173. Min Act: -0.1700

Data Index: 685952 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8486. Min Act: -0.1700

Data Index: 837403 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8173. Min Act: -0.1700

Data Index: 102052 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8017. Min Act: -0.1700

Data Index: 471944 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8173. Min Act: -0.1700

Data Index: 1265250 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 5.2236. Min Range: -5.2236

Max Act: 4.8017. Min Act: -0.1700

Data Index: 962363 (C4 (Web Text))

Max Activating Token Index: 20