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

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

Neuron 1513 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: 3.2049. Min Range: -3.2049

Max Act: 3.2049. Min Act: -0.1700

Data Index: 1207761 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.1577. Min Act: -0.1700

Data Index: 290975 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.1262. Min Act: -0.1700

Data Index: 517490 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0947. Min Act: -0.1700

Data Index: 127061 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0789. Min Act: -0.1700

Data Index: 625433 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1328389 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 275474 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 318429 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 585150 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 1201616 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0631. Min Act: -0.1700

Data Index: 925883 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0631. Min Act: -0.1700

Data Index: 367272 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0631. Min Act: -0.1700

Data Index: 257472 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0631. Min Act: -0.1700

Data Index: 701113 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 363284 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0315. Min Act: -0.1700

Data Index: 93508 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0315. Min Act: -0.1700

Data Index: 1011371 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 1085655 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0473. Min Act: -0.1700

Data Index: 1194653 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.0315. Min Act: -0.1700

Data Index: 539867 (C4 (Web Text))

Max Activating Token Index: 97