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

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

Neuron 987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1833. Min Range: -4.1833

Max Act: 4.1833. Min Act: -0.1700

Data Index: 451055 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.1833. Min Range: -4.1833

Max Act: 4.0583. Min Act: -0.1700

Data Index: 340275 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 4.1833. Min Range: -4.1833

Max Act: 4.0583. Min Act: -0.1700

Data Index: 1013617 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 4.1833. Min Range: -4.1833

Max Act: 4.0270. Min Act: -0.1700

Data Index: 1150343 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9332. Min Act: -0.1700

Data Index: 602256 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 4.1833. Min Range: -4.1833

Max Act: 4.0270. Min Act: -0.1700

Data Index: 953091 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9645. Min Act: -0.1700

Data Index: 66169 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9957. Min Act: -0.1700

Data Index: 1248395 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9332. Min Act: -0.1700

Data Index: 905768 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9019. Min Act: -0.1700

Data Index: 1037497 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9019. Min Act: -0.1700

Data Index: 48768 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8706. Min Act: -0.1700

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.9019. Min Act: -0.1700

Data Index: 453707 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8706. Min Act: -0.1700

Data Index: 1324985 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8394. Min Act: -0.1700

Data Index: 733126 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8706. Min Act: -0.1699

Data Index: 790584 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8394. Min Act: -0.1700

Data Index: 124965 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8394. Min Act: -0.1700

Data Index: 498254 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8394. Min Act: -0.1700

Data Index: 574504 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 4.1833. Min Range: -4.1833

Max Act: 3.8394. Min Act: -0.1700

Data Index: 899385 (C4 (Web Text))

Max Activating Token Index: 545