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

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

Neuron 933 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: 3.5752. Min Range: -3.5752

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1122966 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5596. Min Act: -0.1700

Data Index: 243306 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5596. Min Act: -0.1700

Data Index: 972633 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5439. Min Act: -0.1700

Data Index: 279308 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5439. Min Act: -0.1700

Data Index: 449490 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5439. Min Act: -0.1700

Data Index: 105392 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5283. Min Act: -0.1700

Data Index: 181008 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1027981 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5126. Min Act: -0.1700

Data Index: 113644 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1144249 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.5126. Min Act: -0.1700

Data Index: 1130193 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4969. Min Act: -0.1700

Data Index: 1189989 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4969. Min Act: -0.1700

Data Index: 1359413 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4812. Min Act: -0.1700

Data Index: 264904 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4812. Min Act: -0.1700

Data Index: 354916 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4969. Min Act: -0.1700

Data Index: 983936 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4969. Min Act: -0.1700

Data Index: 568541 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4812. Min Act: -0.1700

Data Index: 639694 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4969. Min Act: -0.1700

Data Index: 150778 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 3.5752. Min Range: -3.5752

Max Act: 3.4812. Min Act: -0.1700

Data Index: 592269 (C4 (Web Text))

Max Activating Token Index: 841