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

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

Neuron 1220 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: 3.5955. Min Range: -3.5955

Max Act: 3.5955. Min Act: -0.1700

Data Index: 489911 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4545. Min Act: -0.1700

Data Index: 115944 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4231. Min Act: -0.1700

Data Index: 410290 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4388. Min Act: -0.1700

Data Index: 408382 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4388. Min Act: -0.1700

Data Index: 916488 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4388. Min Act: -0.1700

Data Index: 431085 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.4231. Min Act: -0.1700

Data Index: 252965 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3917. Min Act: -0.1700

Data Index: 237912 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3917. Min Act: -0.1700

Data Index: 915256 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3917. Min Act: -0.1700

Data Index: 679013 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3760. Min Act: -0.1700

Data Index: 331440 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3290. Min Act: -0.1700

Data Index: 104567 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1180025 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3604. Min Act: -0.1700

Data Index: 1357029 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3604. Min Act: -0.1700

Data Index: 443522 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3760. Min Act: -0.1700

Data Index: 902837 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3447. Min Act: -0.1700

Data Index: 607007 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3133. Min Act: -0.1700

Data Index: 126859 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3290. Min Act: -0.1700

Data Index: 557664 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 3.5955. Min Range: -3.5955

Max Act: 3.3290. Min Act: -0.1700

Data Index: 699471 (C4 (Web Text))

Max Activating Token Index: 878