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

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

Neuron 1500 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: 3.4019. Min Range: -3.4019

Max Act: 3.4019. Min Act: -0.1700

Data Index: 834337 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.3706. Min Act: -0.1700

Data Index: 1215415 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.3078. Min Act: -0.1700

Data Index: 175462 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.2135. Min Act: -0.1700

Data Index: 368015 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.2135. Min Act: -0.1700

Data Index: 795645 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.1820. Min Act: -0.1700

Data Index: 1595001 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1278604 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.1190. Min Act: -0.1700

Data Index: 700290 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0875. Min Act: -0.1700

Data Index: 158708 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0875. Min Act: -0.1700

Data Index: 201952 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 352482 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 412645 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1340762 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1171252 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 182322 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 426381 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1004856 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0243. Min Act: -0.1700

Data Index: 833329 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0559. Min Act: -0.1700

Data Index: 203970 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.4019. Min Range: -3.4019

Max Act: 3.0243. Min Act: -0.1700

Data Index: 221983 (C4 (Web Text))

Max Activating Token Index: 722