Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.4367. Min Act: -0.1700

Data Index: 1044017 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.3742. Min Act: -0.1700

Data Index: 694745 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.2492. Min Act: -0.1700

Data Index: 446647 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.2492. Min Act: -0.1700

Data Index: 416345 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.2805. Min Act: -0.1700

Data Index: 1111761 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1867. Min Act: -0.1700

Data Index: 800409 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1867. Min Act: -0.1700

Data Index: 109414 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1555. Min Act: -0.1700

Data Index: 703762 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1089617 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1242. Min Act: -0.1700

Data Index: 973053 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.1242. Min Act: -0.1700

Data Index: 1110730 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.0617. Min Act: -0.1700

Data Index: 2192 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.0305. Min Act: -0.1700

Data Index: 818565 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9992. Min Act: -0.1700

Data Index: 667298 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9992. Min Act: -0.1700

Data Index: 1242322 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9680. Min Act: -0.1700

Data Index: 42270 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 5.4367. Min Range: -5.4367

Max Act: 5.0617. Min Act: -0.1700

Data Index: 1166148 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9992. Min Act: -0.1700

Data Index: 273760 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9367. Min Act: -0.1700

Data Index: 173783 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 5.4367. Min Range: -5.4367

Max Act: 4.9680. Min Act: -0.1700

Data Index: 174408 (C4 (Web Text))

Max Activating Token Index: 829