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

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

Neuron 914 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.5527. Min Act: -0.1700

Data Index: 713 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4900. Min Act: -0.1700

Data Index: 804393 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4586. Min Act: -0.1700

Data Index: 514771 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4273. Min Act: -0.1700

Data Index: 671912 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4273. Min Act: -0.1700

Data Index: 146026 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 538895 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 169639 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 459807 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 1222430 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 588076 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 991573 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 382881 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 565437 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 295033 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 1195359 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 742906 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3645. Min Act: -0.1700

Data Index: 1308683 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3332. Min Act: -0.1700

Data Index: 71395 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3332. Min Act: -0.1700

Data Index: 763100 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3332. Min Act: -0.1700

Data Index: 981041 (C4 (Web Text))

Max Activating Token Index: 878