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

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

Neuron 1067 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.5565. Min Act: -0.1700

Data Index: 1033149 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.5565. Min Act: -0.1700

Data Index: 659263 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.2753. Min Act: -0.1700

Data Index: 545501 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.2128. Min Act: -0.1700

Data Index: 653845 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.1815. Min Act: -0.1700

Data Index: 1317308 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.1815. Min Act: -0.1700

Data Index: 426850 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.1190. Min Act: -0.1700

Data Index: 899554 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0878. Min Act: -0.1700

Data Index: 767480 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0878. Min Act: -0.1699

Data Index: 801886 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.1190. Min Act: -0.1699

Data Index: 1214136 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0878. Min Act: -0.1700

Data Index: 215939 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.1190. Min Act: -0.1700

Data Index: 518360 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0253. Min Act: -0.1700

Data Index: 306423 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0878. Min Act: -0.1700

Data Index: 855930 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0253. Min Act: -0.1700

Data Index: 538569 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 5.5565. Min Range: -5.5565

Max Act: 5.0253. Min Act: -0.1700

Data Index: 1273276 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 5.5565. Min Range: -5.5565

Max Act: 4.9940. Min Act: -0.1700

Data Index: 131180 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 5.5565. Min Range: -5.5565

Max Act: 4.9940. Min Act: -0.1700

Data Index: 595294 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 5.5565. Min Range: -5.5565

Max Act: 4.9628. Min Act: -0.1700

Data Index: 872366 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 5.5565. Min Range: -5.5565

Max Act: 4.9940. Min Act: -0.1700

Data Index: 1038470 (C4 (Web Text))

Max Activating Token Index: 908