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

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

Neuron 1778 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: 3.1147. Min Range: -3.1147

Max Act: 3.1147. Min Act: -0.1700

Data Index: 892177 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.1147. Min Act: -0.1700

Data Index: 1142032 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.0990. Min Act: -0.1700

Data Index: 932484 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.0990. Min Act: -0.1700

Data Index: 860055 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.0516. Min Act: -0.1700

Data Index: 587987 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.0200. Min Act: -0.1700

Data Index: 568414 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 3.1147. Min Range: -3.1147

Max Act: 3.0042. Min Act: -0.1700

Data Index: 362102 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9726. Min Act: -0.1700

Data Index: 1205305 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9568. Min Act: -0.1700

Data Index: 503183 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9726. Min Act: -0.1700

Data Index: 282866 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9251. Min Act: -0.1700

Data Index: 162576 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9092. Min Act: -0.1700

Data Index: 1220028 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9409. Min Act: -0.1700

Data Index: 154616 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9409. Min Act: -0.1700

Data Index: 110684 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9568. Min Act: -0.1700

Data Index: 349827 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9092. Min Act: -0.1700

Data Index: 342536 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.8934. Min Act: -0.1700

Data Index: 930507 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9092. Min Act: -0.1700

Data Index: 740051 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.9092. Min Act: -0.1700

Data Index: 23550 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 3.1147. Min Range: -3.1147

Max Act: 2.8934. Min Act: -0.1700

Data Index: 980141 (C4 (Web Text))

Max Activating Token Index: 196