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

Dataset: Open Web Text

Neuron 134 in Layer 5

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: 4.0534. Min Range: -4.0534

Max Act: 4.0534. Min Act: -0.1700

Data Index: 4122182 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.9669. Min Act: -0.1700

Data Index: 7261175 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8941. Min Act: -0.1700

Data Index: 4171758 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8777. Min Act: -0.1700

Data Index: 5145666 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.9038. Min Act: -0.1700

Data Index: 978267 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8989. Min Act: -0.1700

Data Index: 5039567 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8692. Min Act: -0.1700

Data Index: 2516155 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8375. Min Act: -0.1700

Data Index: 87767 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8700. Min Act: -0.1700

Data Index: 3870488 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8203. Min Act: -0.1700

Data Index: 3077741 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8554. Min Act: -0.1700

Data Index: 927022 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8589. Min Act: -0.1700

Data Index: 2363246 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8585. Min Act: -0.1700

Data Index: 5661704 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8606. Min Act: -0.1700

Data Index: 5179165 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8527. Min Act: -0.1700

Data Index: 7388288 (Open Web Text)

Max Activating Token Index: 362

Text #15

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8166. Min Act: -0.1700

Data Index: 3534483 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8145. Min Act: -0.1700

Data Index: 7299389 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8262. Min Act: -0.1700

Data Index: 7559031 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8146. Min Act: -0.1700

Data Index: 578680 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 4.0534. Min Range: -4.0534

Max Act: 3.8348. Min Act: -0.1700

Data Index: 31564 (Open Web Text)

Max Activating Token Index: 41