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

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

Neuron 787 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: 7.7320. Min Range: -7.7320

Max Act: 7.7320. Min Act: -0.1700

Data Index: 23283 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.6383. Min Act: -0.1700

Data Index: 843978 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.5758. Min Act: -0.1700

Data Index: 130289 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4820. Min Act: -0.1700

Data Index: 48179 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4195. Min Act: -0.1700

Data Index: 1253405 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.5133. Min Act: -0.1700

Data Index: 234963 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4508. Min Act: -0.1700

Data Index: 624282 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4195. Min Act: -0.1700

Data Index: 364494 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4508. Min Act: -0.1700

Data Index: 523728 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4508. Min Act: -0.1700

Data Index: 178608 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3883. Min Act: -0.1700

Data Index: 627096 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3570. Min Act: -0.1700

Data Index: 72798 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3883. Min Act: -0.1700

Data Index: 1106459 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3883. Min Act: -0.1700

Data Index: 489383 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4195. Min Act: -0.1700

Data Index: 325491 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3883. Min Act: -0.1700

Data Index: 516667 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.4508. Min Act: -0.1700

Data Index: 450690 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3258. Min Act: -0.1700

Data Index: 954150 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3258. Min Act: -0.1700

Data Index: 618011 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 7.7320. Min Range: -7.7320

Max Act: 7.3570. Min Act: -0.1700

Data Index: 1064602 (C4 (Web Text))

Max Activating Token Index: 268