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

Dataset: Open Web Text

Neuron 1213 in Layer 3

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: 3.3599. Min Range: -3.3599

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1847225 (Open Web Text)

Max Activating Token Index: 857

Text #1

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.3121. Min Act: -0.1700

Data Index: 635777 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1482969 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2907. Min Act: -0.1700

Data Index: 7819493 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2647. Min Act: -0.1700

Data Index: 553272 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2599. Min Act: -0.1700

Data Index: 7496897 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2628. Min Act: -0.1700

Data Index: 6805459 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2283. Min Act: -0.1700

Data Index: 1190919 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1943. Min Act: -0.1700

Data Index: 1493151 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1922. Min Act: -0.1700

Data Index: 8337722 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1817. Min Act: -0.1700

Data Index: 5854375 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1927. Min Act: -0.1700

Data Index: 1185085 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1867. Min Act: -0.1700

Data Index: 7728159 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1860. Min Act: -0.1700

Data Index: 687647 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1968. Min Act: -0.1700

Data Index: 7181504 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2032. Min Act: -0.1700

Data Index: 201839 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1538. Min Act: -0.1700

Data Index: 962661 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1463. Min Act: -0.1700

Data Index: 552700 (Open Web Text)

Max Activating Token Index: 734

Text #18

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1705. Min Act: -0.1700

Data Index: 5353968 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1777. Min Act: -0.1700

Data Index: 7131968 (Open Web Text)

Max Activating Token Index: 29