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

Dataset: Open Web Text

Neuron 161 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: 5.4340. Min Range: -5.4340

Max Act: 5.4340. Min Act: -0.1700

Data Index: 7470553 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.3333. Min Act: -0.1700

Data Index: 7470552 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2806. Min Act: -0.1700

Data Index: 2983065 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2834. Min Act: -0.1700

Data Index: 2332630 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2420. Min Act: -0.1700

Data Index: 7912968 (Open Web Text)

Max Activating Token Index: 340

Text #5

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2076. Min Act: -0.1700

Data Index: 5773097 (Open Web Text)

Max Activating Token Index: 706

Text #6

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1870. Min Act: -0.1700

Data Index: 6918630 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1909. Min Act: -0.1700

Data Index: 8816045 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1342. Min Act: -0.1700

Data Index: 636260 (Open Web Text)

Max Activating Token Index: 374

Text #9

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1708. Min Act: -0.1700

Data Index: 8002579 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1321. Min Act: -0.1700

Data Index: 4875547 (Open Web Text)

Max Activating Token Index: 244

Text #11

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1065. Min Act: -0.1700

Data Index: 4500646 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0959. Min Act: -0.1700

Data Index: 6553580 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1121. Min Act: -0.1700

Data Index: 2642537 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1020. Min Act: -0.1700

Data Index: 2643069 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1001. Min Act: -0.1700

Data Index: 7150866 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0900. Min Act: -0.1700

Data Index: 5572778 (Open Web Text)

Max Activating Token Index: 566

Text #17

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1108. Min Act: -0.1700

Data Index: 5100404 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0829. Min Act: -0.1700

Data Index: 3471642 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0914. Min Act: -0.1700

Data Index: 6766499 (Open Web Text)

Max Activating Token Index: 72