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

Dataset: Open Web Text

Neuron 43 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: 2.9132. Min Range: -2.9132

Max Act: 2.9132. Min Act: -0.1700

Data Index: 6999041 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.9003. Min Act: -0.1700

Data Index: 2773948 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8599. Min Act: -0.1700

Data Index: 8329059 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8590. Min Act: -0.1700

Data Index: 8595076 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8427. Min Act: -0.1700

Data Index: 606618 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8562. Min Act: -0.1700

Data Index: 7090937 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8527. Min Act: -0.1700

Data Index: 8391392 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8363. Min Act: -0.1700

Data Index: 4923356 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8249. Min Act: -0.1700

Data Index: 3835676 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8181. Min Act: -0.1700

Data Index: 3708383 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8216. Min Act: -0.1700

Data Index: 5980355 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8214. Min Act: -0.1700

Data Index: 8728577 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8160. Min Act: -0.1700

Data Index: 361416 (Open Web Text)

Max Activating Token Index: 785

Text #13

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8017. Min Act: -0.1700

Data Index: 4517866 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8030. Min Act: -0.1700

Data Index: 8400747 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8080. Min Act: -0.1700

Data Index: 6556786 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8074. Min Act: -0.1700

Data Index: 6999042 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7989. Min Act: -0.1700

Data Index: 1872698 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7998. Min Act: -0.1700

Data Index: 1871669 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8075. Min Act: -0.1700

Data Index: 5892860 (Open Web Text)

Max Activating Token Index: 108