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

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

Neuron 839 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: 5.2931. Min Range: -5.2931

Max Act: 5.2931. Min Act: -0.1700

Data Index: 101969 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 5.2931. Min Range: -5.2931

Max Act: 5.1993. Min Act: -0.1700

Data Index: 873174 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 5.2931. Min Range: -5.2931

Max Act: 5.1681. Min Act: -0.1700

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.9493. Min Act: -0.1700

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.9181. Min Act: -0.1700

Data Index: 1325379 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.9493. Min Act: -0.1700

Data Index: 773873 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.8868. Min Act: -0.1700

Data Index: 968 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.8556. Min Act: -0.1700

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.8243. Min Act: -0.1700

Data Index: 451576 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7931. Min Act: -0.1700

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7931. Min Act: -0.1700

Data Index: 704011 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7931. Min Act: -0.1700

Data Index: 723173 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7931. Min Act: -0.1700

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7618. Min Act: -0.1700

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7618. Min Act: -0.1700

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.6993. Min Act: -0.1700

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7931. Min Act: -0.1700

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7306. Min Act: -0.1700

Data Index: 170551 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.7618. Min Act: -0.1700

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 5.2931. Min Range: -5.2931

Max Act: 4.6056. Min Act: -0.1700

Data Index: 1249555 (C4 (Web Text))

Max Activating Token Index: 980