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

Dataset: Open Web Text

Neuron 1043 in Layer 2

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: 3.0866. Min Range: -3.0866

Max Act: 3.0866. Min Act: -0.1700

Data Index: 530714 (Open Web Text)

Max Activating Token Index: 840

Text #1

Max Range: 3.0866. Min Range: -3.0866

Max Act: 3.0580. Min Act: -0.1700

Data Index: 3543022 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.0866. Min Range: -3.0866

Max Act: 3.0119. Min Act: -0.1700

Data Index: 6980183 (Open Web Text)

Max Activating Token Index: 628

Text #3

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9928. Min Act: -0.1700

Data Index: 4726999 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9839. Min Act: -0.1700

Data Index: 1974749 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9895. Min Act: -0.1700

Data Index: 8093958 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9659. Min Act: -0.1700

Data Index: 4086786 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9860. Min Act: -0.1700

Data Index: 6033937 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9433. Min Act: -0.1700

Data Index: 3757879 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9342. Min Act: -0.1700

Data Index: 1011053 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9138. Min Act: -0.1700

Data Index: 1102048 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9646. Min Act: -0.1700

Data Index: 4142167 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9077. Min Act: -0.1700

Data Index: 8261679 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9209. Min Act: -0.1700

Data Index: 7527175 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9175. Min Act: -0.1700

Data Index: 6257270 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9047. Min Act: -0.1700

Data Index: 2490482 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9109. Min Act: -0.1700

Data Index: 8447867 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.8599. Min Act: -0.1700

Data Index: 6823875 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.9195. Min Act: -0.1700

Data Index: 7702879 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.0866. Min Range: -3.0866

Max Act: 2.8836. Min Act: -0.1700

Data Index: 1585705 (Open Web Text)

Max Activating Token Index: 29