Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.7414. Min Act: -0.1700

Data Index: 1687608 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.7270. Min Act: -0.1700

Data Index: 6684659 (Open Web Text)

Max Activating Token Index: 676

Text #2

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6927. Min Act: -0.1700

Data Index: 1857887 (Open Web Text)

Max Activating Token Index: 246

Text #3

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6392. Min Act: -0.1700

Data Index: 5154464 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6351. Min Act: -0.1700

Data Index: 1664847 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6600. Min Act: -0.1700

Data Index: 5791114 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6671. Min Act: -0.1700

Data Index: 8264705 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6673. Min Act: -0.1700

Data Index: 7884145 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6295. Min Act: -0.1700

Data Index: 8797956 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6001. Min Act: -0.1700

Data Index: 6071175 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5925. Min Act: -0.1700

Data Index: 1424792 (Open Web Text)

Max Activating Token Index: 384

Text #11

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5853. Min Act: -0.1700

Data Index: 1535692 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6081. Min Act: -0.1700

Data Index: 3314418 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6032. Min Act: -0.1700

Data Index: 5261091 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5768. Min Act: -0.1700

Data Index: 6691478 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5890. Min Act: -0.1700

Data Index: 7629165 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.6088. Min Act: -0.1700

Data Index: 3557588 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5843. Min Act: -0.1700

Data Index: 835139 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5884. Min Act: -0.1700

Data Index: 7706524 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 4.7414. Min Range: -4.7414

Max Act: 4.5666. Min Act: -0.1700

Data Index: 875151 (Open Web Text)

Max Activating Token Index: 1000