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

Dataset: Open Web Text

Neuron 1710 in Layer 0

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: 4.9617. Min Range: -4.9617

Max Act: 4.9385. Min Act: -0.1687

Data Index: 6549672 (Open Web Text)

Max Activating Token Index: 318

Text #1

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.9617. Min Act: -0.1653

Data Index: 8567615 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.9268. Min Act: -0.1700

Data Index: 611099 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.8805. Min Act: -0.1700

Data Index: 8557775 (Open Web Text)

Max Activating Token Index: 102

Text #4

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.8928. Min Act: -0.1700

Data Index: 22536 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.8834. Min Act: -0.1453

Data Index: 7425356 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.8380. Min Act: -0.1699

Data Index: 4278902 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7960. Min Act: -0.1700

Data Index: 1577244 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.8016. Min Act: -0.1700

Data Index: 1992610 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7986. Min Act: -0.1700

Data Index: 4354272 (Open Web Text)

Max Activating Token Index: 668

Text #10

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7501. Min Act: -0.1633

Data Index: 1210251 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7685. Min Act: -0.1632

Data Index: 3228706 (Open Web Text)

Max Activating Token Index: 299

Text #12

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7263. Min Act: -0.1699

Data Index: 2057592 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7326. Min Act: -0.1675

Data Index: 629236 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7120. Min Act: -0.1579

Data Index: 553537 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.7005. Min Act: -0.1700

Data Index: 5668884 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.6788. Min Act: -0.1700

Data Index: 1210253 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.6489. Min Act: -0.1700

Data Index: 8694317 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.6352. Min Act: -0.1700

Data Index: 2920543 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 4.9617. Min Range: -4.9617

Max Act: 4.6633. Min Act: -0.1695

Data Index: 2907956 (Open Web Text)

Max Activating Token Index: 538