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

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

Neuron 1587 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: 3.7476. Min Range: -3.7476

Max Act: 3.7476. Min Act: -0.1700

Data Index: 1187161 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6850. Min Act: -0.1700

Data Index: 226334 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.7006. Min Act: -0.1700

Data Index: 694859 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6380. Min Act: -0.1700

Data Index: 110184 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6537. Min Act: -0.1700

Data Index: 1359195 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6693. Min Act: -0.1700

Data Index: 715979 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6537. Min Act: -0.1700

Data Index: 458878 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1000457 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6224. Min Act: -0.1700

Data Index: 634976 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1545620 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 853061 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6224. Min Act: -0.1700

Data Index: 875703 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.5911. Min Act: -0.1700

Data Index: 881572 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1280550 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.5911. Min Act: -0.1700

Data Index: 590446 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 313237 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1062676 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.6067. Min Act: -0.1700

Data Index: 409233 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.5754. Min Act: -0.1700

Data Index: 804586 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.7476. Min Range: -3.7476

Max Act: 3.5754. Min Act: -0.1700

Data Index: 836626 (C4 (Web Text))

Max Activating Token Index: 484