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

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

Neuron 1473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5782. Min Act: -0.1700

Data Index: 488915 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5470. Min Act: -0.1700

Data Index: 604584 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5470. Min Act: -0.1700

Data Index: 760259 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.6407. Min Act: -0.1700

Data Index: 806185 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4845. Min Act: -0.1700

Data Index: 779689 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5470. Min Act: -0.1700

Data Index: 207490 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5157. Min Act: -0.1700

Data Index: 132530 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5470. Min Act: -0.1700

Data Index: 1257798 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4845. Min Act: -0.1700

Data Index: 260896 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4845. Min Act: -0.1700

Data Index: 493395 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4532. Min Act: -0.1700

Data Index: 912006 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4845. Min Act: -0.1700

Data Index: 677404 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4532. Min Act: -0.1700

Data Index: 473414 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4532. Min Act: -0.1700

Data Index: 860200 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4532. Min Act: -0.1700

Data Index: 933308 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4220. Min Act: -0.1700

Data Index: 825934 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.5157. Min Act: -0.1700

Data Index: 97242 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4532. Min Act: -0.1700

Data Index: 261121 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.4220. Min Act: -0.1700

Data Index: 742682 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 5.6407. Min Range: -5.6407

Max Act: 5.3907. Min Act: -0.1700

Data Index: 636090 (C4 (Web Text))

Max Activating Token Index: 393