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

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

Neuron 1102 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.2190. Min Act: -0.1700

Data Index: 1295303 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.2190. Min Act: -0.1700

Data Index: 744687 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.2190. Min Act: -0.1700

Data Index: 565545 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1877. Min Act: -0.1700

Data Index: 1070355 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.2190. Min Act: -0.1700

Data Index: 1233980 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1565. Min Act: -0.1700

Data Index: 1217554 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1565. Min Act: -0.1700

Data Index: 1036869 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0627. Min Act: -0.1700

Data Index: 1194545 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1252. Min Act: -0.1700

Data Index: 812210 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0940. Min Act: -0.1700

Data Index: 213046 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1252. Min Act: -0.1700

Data Index: 957007 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1252. Min Act: -0.1700

Data Index: 675049 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1252. Min Act: -0.1700

Data Index: 523625 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0940. Min Act: -0.1700

Data Index: 721038 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.1252. Min Act: -0.1700

Data Index: 528078 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0940. Min Act: -0.1700

Data Index: 1215328 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0627. Min Act: -0.1700

Data Index: 659914 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0627. Min Act: -0.1700

Data Index: 230618 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0940. Min Act: -0.1700

Data Index: 34542 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 5.2190. Min Range: -5.2190

Max Act: 5.0627. Min Act: -0.1700

Data Index: 1240394 (C4 (Web Text))

Max Activating Token Index: 888