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

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

Neuron 871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.7047. Min Act: -0.1700

Data Index: 275512 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5481. Min Act: -0.1700

Data Index: 287874 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5481. Min Act: -0.1700

Data Index: 687314 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5481. Min Act: -0.1700

Data Index: 1300260 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5481. Min Act: -0.1700

Data Index: 995043 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5168. Min Act: -0.1700

Data Index: 487530 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4541. Min Act: -0.1700

Data Index: 747074 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5481. Min Act: -0.1700

Data Index: 328367 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 230995 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 13219 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5168. Min Act: -0.1700

Data Index: 163748 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 989467 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 1082605 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4541. Min Act: -0.1700

Data Index: 558575 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5168. Min Act: -0.1700

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5794. Min Act: -0.1700

Data Index: 853264 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 643325 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4855. Min Act: -0.1700

Data Index: 1051004 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4228. Min Act: -0.1700

Data Index: 955649 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4228. Min Act: -0.1700

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 543