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

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

Neuron 1764 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: 6.3761. Min Range: -6.3761

Max Act: 6.3761. Min Act: -0.1700

Data Index: 162880 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.3449. Min Act: -0.1700

Data Index: 1152636 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.3136. Min Act: -0.1699

Data Index: 1021801 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.2824. Min Act: -0.1700

Data Index: 387298 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.1574. Min Act: -0.1700

Data Index: 1079320 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.1261. Min Act: -0.1700

Data Index: 142465 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.1261. Min Act: -0.1700

Data Index: 713671 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0636. Min Act: -0.1700

Data Index: 378209 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0636. Min Act: -0.1688

Data Index: 272800 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0636. Min Act: -0.1700

Data Index: 908291 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0636. Min Act: -0.1700

Data Index: 744141 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0324. Min Act: -0.1700

Data Index: 1217110 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0324. Min Act: -0.1700

Data Index: 577665 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0324. Min Act: -0.1700

Data Index: 343862 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 6.3761. Min Range: -6.3761

Max Act: 5.9699. Min Act: -0.1700

Data Index: 989373 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0324. Min Act: -0.1700

Data Index: 238415 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0324. Min Act: -0.1700

Data Index: 51825 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 6.3761. Min Range: -6.3761

Max Act: 5.9699. Min Act: -0.1700

Data Index: 904579 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 6.3761. Min Range: -6.3761

Max Act: 6.0011. Min Act: -0.1700

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 6.3761. Min Range: -6.3761

Max Act: 5.9699. Min Act: -0.1700

Data Index: 666778 (C4 (Web Text))

Max Activating Token Index: 105