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

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

Neuron 1250 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.1899. Min Act: -0.1700

Data Index: 739715 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.1270. Min Act: -0.1700

Data Index: 1322497 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.1270. Min Act: -0.1700

Data Index: 1097684 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0797. Min Act: -0.1700

Data Index: 629643 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0639. Min Act: -0.1700

Data Index: 439435 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0481. Min Act: -0.1700

Data Index: 499135 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0165. Min Act: -0.1700

Data Index: 1335718 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0165. Min Act: -0.1700

Data Index: 961227 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0007. Min Act: -0.1700

Data Index: 474277 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 3.1899. Min Range: -3.1899

Max Act: 3.0165. Min Act: -0.1700

Data Index: 1123456 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9849. Min Act: -0.1700

Data Index: 1301647 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9691. Min Act: -0.1700

Data Index: 919626 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9532. Min Act: -0.1700

Data Index: 20859 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9532. Min Act: -0.1700

Data Index: 533121 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9532. Min Act: -0.1700

Data Index: 763119 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9216. Min Act: -0.1700

Data Index: 1210727 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9374. Min Act: -0.1700

Data Index: 855345 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9216. Min Act: -0.1700

Data Index: 837359 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9374. Min Act: -0.1700

Data Index: 370569 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.1899. Min Range: -3.1899

Max Act: 2.9216. Min Act: -0.1700

Data Index: 469827 (C4 (Web Text))

Max Activating Token Index: 755