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

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

Neuron 1702 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: 3.6868. Min Range: -3.6868

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1378233 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1649278 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6399. Min Act: -0.1700

Data Index: 1556910 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1421204 (Python Code)

Max Activating Token Index: 468

Text #4

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 398248 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1445220 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1573661 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1620059 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1475587 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 210488 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6399. Min Act: -0.1700

Data Index: 1254562 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 804188 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1391603 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1535338 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6086. Min Act: -0.1700

Data Index: 982293 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 530592 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 700617 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 622775 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1289500 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 3.6868. Min Range: -3.6868

Max Act: 3.6086. Min Act: -0.1700

Data Index: 452494 (C4 (Web Text))

Max Activating Token Index: 347