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

Dataset: Open Web Text

Neuron 642 in Layer 6

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: 2.4822. Min Range: -2.4822

Max Act: 2.4822. Min Act: -0.1700

Data Index: 7276354 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.4350. Min Act: -0.1700

Data Index: 8581787 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.4206. Min Act: -0.1700

Data Index: 6716843 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.4284. Min Act: -0.1700

Data Index: 5256427 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.4128. Min Act: -0.1700

Data Index: 8153392 (Open Web Text)

Max Activating Token Index: 654

Text #5

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.4060. Min Act: -0.1700

Data Index: 2092429 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3761. Min Act: -0.1700

Data Index: 5176528 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3847. Min Act: -0.1700

Data Index: 2780838 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3812. Min Act: -0.1700

Data Index: 5750806 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3857. Min Act: -0.1700

Data Index: 2678295 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3663. Min Act: -0.1700

Data Index: 2598888 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3644. Min Act: -0.1700

Data Index: 7297739 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3521. Min Act: -0.1700

Data Index: 3673812 (Open Web Text)

Max Activating Token Index: 556

Text #13

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3853. Min Act: -0.1700

Data Index: 5252973 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3548. Min Act: -0.1700

Data Index: 1010421 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3535. Min Act: -0.1700

Data Index: 1346096 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3459. Min Act: -0.1700

Data Index: 4491569 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3520. Min Act: -0.1700

Data Index: 509398 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3536. Min Act: -0.1700

Data Index: 879962 (Open Web Text)

Max Activating Token Index: 786

Text #19

Max Range: 2.4822. Min Range: -2.4822

Max Act: 2.3227. Min Act: -0.1700

Data Index: 4675003 (Open Web Text)

Max Activating Token Index: 682