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

Dataset: Open Web Text

Neuron 1535 in Layer 2

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: 1.8433. Min Range: -1.8433

Max Act: 1.8433. Min Act: -0.1700

Data Index: 2476367 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.8276. Min Act: -0.1700

Data Index: 3816287 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.8098. Min Act: -0.1700

Data Index: 4638189 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7640. Min Act: -0.1700

Data Index: 7490355 (Open Web Text)

Max Activating Token Index: 923

Text #4

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7708. Min Act: -0.1700

Data Index: 1753056 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7586. Min Act: -0.1700

Data Index: 6604186 (Open Web Text)

Max Activating Token Index: 394

Text #6

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7585. Min Act: -0.1700

Data Index: 6096855 (Open Web Text)

Max Activating Token Index: 138

Text #7

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7471. Min Act: -0.1700

Data Index: 7997511 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7267. Min Act: -0.1700

Data Index: 4718414 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7495. Min Act: -0.1700

Data Index: 5050420 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7339. Min Act: -0.1699

Data Index: 6604198 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7313. Min Act: -0.1700

Data Index: 3971837 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7218. Min Act: -0.1700

Data Index: 6604189 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7229. Min Act: -0.1700

Data Index: 115749 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7211. Min Act: -0.1700

Data Index: 3971836 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7239. Min Act: -0.1700

Data Index: 896810 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.6940. Min Act: -0.1700

Data Index: 2230107 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7009. Min Act: -0.1700

Data Index: 1175718 (Open Web Text)

Max Activating Token Index: 692

Text #18

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7047. Min Act: -0.1700

Data Index: 4638188 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.6957. Min Act: -0.1700

Data Index: 893288 (Open Web Text)

Max Activating Token Index: 729