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

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

Neuron 1019 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: 4.0495. Min Range: -4.0495

Max Act: 4.0495. Min Act: -0.1700

Data Index: 381018 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.9244. Min Act: -0.1700

Data Index: 287988 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.8306. Min Act: -0.1700

Data Index: 892445 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.8619. Min Act: -0.1700

Data Index: 610949 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.8619. Min Act: -0.1700

Data Index: 503785 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7993. Min Act: -0.1700

Data Index: 925774 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7680. Min Act: -0.1700

Data Index: 530255 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7680. Min Act: -0.1700

Data Index: 420360 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7680. Min Act: -0.1700

Data Index: 1272502 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7680. Min Act: -0.1700

Data Index: 29974 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 47813 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 789227 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 799050 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7055. Min Act: -0.1700

Data Index: 855726 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 975986 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 339535 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7680. Min Act: -0.1700

Data Index: 753151 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 612095 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.7368. Min Act: -0.1700

Data Index: 1066589 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 4.0495. Min Range: -4.0495

Max Act: 3.6742. Min Act: -0.1700

Data Index: 397374 (C4 (Web Text))

Max Activating Token Index: 80