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

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

Neuron 1592 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.2971. Min Act: -0.1700

Data Index: 238014 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.5159. Min Act: -0.1700

Data Index: 1129650 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.3284. Min Act: -0.1700

Data Index: 734361 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.1409. Min Act: -0.1700

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.2346. Min Act: -0.1700

Data Index: 282732 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.9221. Min Act: -0.1700

Data Index: 1298804 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.2346. Min Act: -0.1700

Data Index: 984706 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.2034. Min Act: -0.1700

Data Index: 1060869 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.1096. Min Act: -0.1700

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.9221. Min Act: -0.1700

Data Index: 1150460 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8284. Min Act: -0.1700

Data Index: 725692 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.9534. Min Act: -0.1700

Data Index: 327575 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8909. Min Act: -0.1700

Data Index: 86627 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.7034. Min Act: -0.1700

Data Index: 1193 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 7.5159. Min Range: -7.5159

Max Act: 7.0784. Min Act: -0.1700

Data Index: 594831 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8909. Min Act: -0.1700

Data Index: 605628 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8284. Min Act: -0.1700

Data Index: 1259292 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.6409. Min Act: -0.1700

Data Index: 1139766 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8596. Min Act: -0.1700

Data Index: 632726 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 7.5159. Min Range: -7.5159

Max Act: 6.8284. Min Act: -0.1700

Data Index: 320460 (C4 (Web Text))

Max Activating Token Index: 503