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

Dataset: Open Web Text

Neuron 1796 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: 2.8313. Min Range: -2.8313

Max Act: 2.8313. Min Act: -0.1700

Data Index: 2068495 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.7498. Min Act: -0.1700

Data Index: 6911311 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.7129. Min Act: -0.1700

Data Index: 5989541 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.7170. Min Act: -0.1700

Data Index: 8642614 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6869. Min Act: -0.1700

Data Index: 3654759 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6928. Min Act: -0.1700

Data Index: 5064491 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6958. Min Act: -0.1700

Data Index: 22241 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6976. Min Act: -0.1700

Data Index: 2340163 (Open Web Text)

Max Activating Token Index: 797

Text #8

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6634. Min Act: -0.1700

Data Index: 6438579 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6707. Min Act: -0.1700

Data Index: 3865636 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6884. Min Act: -0.1700

Data Index: 5994258 (Open Web Text)

Max Activating Token Index: 544

Text #11

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.7022. Min Act: -0.1700

Data Index: 4136294 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6759. Min Act: -0.1700

Data Index: 4210567 (Open Web Text)

Max Activating Token Index: 193

Text #13

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6608. Min Act: -0.1700

Data Index: 6386290 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6695. Min Act: -0.1700

Data Index: 7888327 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6658. Min Act: -0.1700

Data Index: 3874366 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6411. Min Act: -0.1700

Data Index: 2858538 (Open Web Text)

Max Activating Token Index: 823

Text #17

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6555. Min Act: -0.1700

Data Index: 2700186 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6555. Min Act: -0.1700

Data Index: 5902349 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6392. Min Act: -0.1700

Data Index: 2595402 (Open Web Text)

Max Activating Token Index: 144