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

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

Neuron 607 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: 7.9033. Min Range: -7.9033

Max Act: 7.9033. Min Act: -0.1700

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.5596. Min Act: -0.1700

Data Index: 1271673 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.5908. Min Act: -0.1700

Data Index: 1300686 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.5283. Min Act: -0.1700

Data Index: 187956 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.4658. Min Act: -0.1700

Data Index: 357419 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.4658. Min Act: -0.1700

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3721. Min Act: -0.1700

Data Index: 774549 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.4346. Min Act: -0.1700

Data Index: 863516 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3721. Min Act: -0.1700

Data Index: 1152214 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3721. Min Act: -0.1700

Data Index: 94590 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3721. Min Act: -0.1700

Data Index: 408784 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3721. Min Act: -0.1700

Data Index: 1280038 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3096. Min Act: -0.1700

Data Index: 867372 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.2783. Min Act: -0.1700

Data Index: 980366 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3096. Min Act: -0.1700

Data Index: 112715 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.2783. Min Act: -0.1700

Data Index: 344290 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.3096. Min Act: -0.1700

Data Index: 1123307 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.2783. Min Act: -0.1700

Data Index: 407126 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.2783. Min Act: -0.1700

Data Index: 1154521 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 7.9033. Min Range: -7.9033

Max Act: 7.2471. Min Act: -0.1700

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 379