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

Dataset: Open Web Text

Neuron 738 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: 2.8556. Min Range: -2.8556

Max Act: 2.8556. Min Act: -0.1700

Data Index: 7281853 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.8193. Min Act: -0.1700

Data Index: 5758640 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.8156. Min Act: -0.1700

Data Index: 2348498 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.8066. Min Act: -0.1700

Data Index: 7916321 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.8168. Min Act: -0.1700

Data Index: 7195396 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7691. Min Act: -0.1700

Data Index: 2142382 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7776. Min Act: -0.1700

Data Index: 3615122 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7768. Min Act: -0.1700

Data Index: 2696162 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7729. Min Act: -0.1700

Data Index: 4044010 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7571. Min Act: -0.1700

Data Index: 275541 (Open Web Text)

Max Activating Token Index: 630

Text #10

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7538. Min Act: -0.1700

Data Index: 7782417 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7485. Min Act: -0.1700

Data Index: 4810874 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7532. Min Act: -0.1700

Data Index: 6707152 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7433. Min Act: -0.1700

Data Index: 7500356 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7532. Min Act: -0.1700

Data Index: 8301901 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7398. Min Act: -0.1700

Data Index: 1102865 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7471. Min Act: -0.1700

Data Index: 7963665 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7430. Min Act: -0.1700

Data Index: 5876625 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7195. Min Act: -0.1700

Data Index: 2971886 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7227. Min Act: -0.1700

Data Index: 3126770 (Open Web Text)

Max Activating Token Index: 645