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

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

Neuron 1060 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9833. Min Act: -0.1700

Data Index: 811313 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9990. Min Act: -0.1700

Data Index: 284134 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9677. Min Act: -0.1700

Data Index: 1341871 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9833. Min Act: -0.1700

Data Index: 78521 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9364. Min Act: -0.1700

Data Index: 1102136 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9364. Min Act: -0.1700

Data Index: 723058 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9364. Min Act: -0.1700

Data Index: 59379 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9208. Min Act: -0.1700

Data Index: 354069 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9521. Min Act: -0.1700

Data Index: 924784 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8739. Min Act: -0.1700

Data Index: 239328 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9208. Min Act: -0.1700

Data Index: 1139500 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9208. Min Act: -0.1700

Data Index: 538471 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8739. Min Act: -0.1700

Data Index: 230325 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8895. Min Act: -0.1700

Data Index: 54592 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.9052. Min Act: -0.1700

Data Index: 587182 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8895. Min Act: -0.1700

Data Index: 686203 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8739. Min Act: -0.1700

Data Index: 42549 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8739. Min Act: -0.1700

Data Index: 817906 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8426. Min Act: -0.1700

Data Index: 260038 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.9990. Min Range: -3.9990

Max Act: 3.8739. Min Act: -0.1700

Data Index: 1339206 (C4 (Web Text))

Max Activating Token Index: 517