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

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

Neuron 477 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: 3.6117. Min Range: -3.6117

Max Act: 3.6117. Min Act: -0.1700

Data Index: 462399 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4550. Min Act: -0.1700

Data Index: 869977 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4550. Min Act: -0.1700

Data Index: 801906 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4550. Min Act: -0.1700

Data Index: 984780 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4237. Min Act: -0.1700

Data Index: 1091342 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3609. Min Act: -0.1700

Data Index: 16891 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4550. Min Act: -0.1700

Data Index: 981675 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4237. Min Act: -0.1700

Data Index: 376290 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4237. Min Act: -0.1700

Data Index: 308008 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.4237. Min Act: -0.1700

Data Index: 105281 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3609. Min Act: -0.1700

Data Index: 733423 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3923. Min Act: -0.1700

Data Index: 532148 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3609. Min Act: -0.1700

Data Index: 968933 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3609. Min Act: -0.1700

Data Index: 442637 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3609. Min Act: -0.1700

Data Index: 771199 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.2981. Min Act: -0.1700

Data Index: 23527 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3923. Min Act: -0.1700

Data Index: 722982 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.3295. Min Act: -0.1700

Data Index: 130720 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.2981. Min Act: -0.1700

Data Index: 28341 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.6117. Min Range: -3.6117

Max Act: 3.2667. Min Act: -0.1700

Data Index: 119519 (C4 (Web Text))

Max Activating Token Index: 526