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

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

Neuron 987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9799. Min Act: -0.1700

Data Index: 235482 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9799. Min Act: -0.1700

Data Index: 972806 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 5.0112. Min Range: -5.0112

Max Act: 5.0112. Min Act: -0.1700

Data Index: 1118733 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 1125956 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 1298624 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 867117 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 1189029 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 1184514 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 206473 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8862. Min Act: -0.1700

Data Index: 132373 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 836273 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 453247 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 105376 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 376776 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 145317 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8862. Min Act: -0.1700

Data Index: 38970 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 23064 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 961122 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.8549. Min Act: -0.1700

Data Index: 195590 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 5.0112. Min Range: -5.0112

Max Act: 4.9174. Min Act: -0.1700

Data Index: 816507 (C4 (Web Text))

Max Activating Token Index: 691