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

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

Neuron 630 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: 5.7555. Min Range: -5.7555

Max Act: 5.7555. Min Act: -0.1700

Data Index: 86882 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2868. Min Act: -0.1700

Data Index: 520322 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.4118. Min Act: -0.1700

Data Index: 827292 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3805. Min Act: -0.1700

Data Index: 153253 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.4118. Min Act: -0.1700

Data Index: 967260 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3805. Min Act: -0.1700

Data Index: 316207 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3493. Min Act: -0.1700

Data Index: 527244 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3493. Min Act: -0.1700

Data Index: 677743 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2868. Min Act: -0.1700

Data Index: 441084 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3180. Min Act: -0.1700

Data Index: 497644 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2868. Min Act: -0.1700

Data Index: 1498191 (Python Code)

Max Activating Token Index: 705

Text #11

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3180. Min Act: -0.1700

Data Index: 596209 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2243. Min Act: -0.1700

Data Index: 75236 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2868. Min Act: -0.1700

Data Index: 1001752 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2868. Min Act: -0.1700

Data Index: 454614 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2555. Min Act: -0.1700

Data Index: 1322332 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2243. Min Act: -0.1700

Data Index: 1322704 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.1930. Min Act: -0.1700

Data Index: 647311 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.1618. Min Act: -0.1700

Data Index: 308475 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.1618. Min Act: -0.1700

Data Index: 521893 (C4 (Web Text))

Max Activating Token Index: 219