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

Dataset: Open Web Text

Neuron 2559 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: 4.2258. Min Range: -4.2258

Max Act: 4.2258. Min Act: -0.1700

Data Index: 7719301 (Open Web Text)

Max Activating Token Index: 449

Text #1

Max Range: 4.2258. Min Range: -4.2258

Max Act: 4.0487. Min Act: -0.1700

Data Index: 393561 (Open Web Text)

Max Activating Token Index: 910

Text #2

Max Range: 4.2258. Min Range: -4.2258

Max Act: 4.0295. Min Act: -0.1700

Data Index: 8285100 (Open Web Text)

Max Activating Token Index: 856

Text #3

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9862. Min Act: -0.1700

Data Index: 8562299 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9379. Min Act: -0.1700

Data Index: 8350394 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9409. Min Act: -0.1700

Data Index: 7528822 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9565. Min Act: -0.1700

Data Index: 2235024 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9446. Min Act: -0.1700

Data Index: 380758 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9498. Min Act: -0.1700

Data Index: 2420067 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9410. Min Act: -0.1700

Data Index: 539342 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9165. Min Act: -0.1700

Data Index: 411836 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9052. Min Act: -0.1700

Data Index: 344206 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8758. Min Act: -0.1700

Data Index: 5884029 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8793. Min Act: -0.1700

Data Index: 3884047 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8888. Min Act: -0.1700

Data Index: 2758234 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8811. Min Act: -0.1700

Data Index: 665151 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9151. Min Act: -0.1700

Data Index: 1705780 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.9167. Min Act: -0.1700

Data Index: 7602258 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8828. Min Act: -0.1700

Data Index: 3685547 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 4.2258. Min Range: -4.2258

Max Act: 3.8889. Min Act: -0.1700

Data Index: 6463512 (Open Web Text)

Max Activating Token Index: 69