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

Dataset: Open Web Text

Neuron 3 in Layer 4

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: 3.0881. Min Range: -3.0881

Max Act: 3.0555. Min Act: -0.1700

Data Index: 2723320 (Open Web Text)

Max Activating Token Index: 111

Text #1

Max Range: 3.0881. Min Range: -3.0881

Max Act: 3.0881. Min Act: -0.1700

Data Index: 6530860 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 3.0881. Min Range: -3.0881

Max Act: 3.0539. Min Act: -0.1700

Data Index: 3781737 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.0881. Min Range: -3.0881

Max Act: 3.0424. Min Act: -0.1700

Data Index: 1871296 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 3.0881. Min Range: -3.0881

Max Act: 3.0358. Min Act: -0.1700

Data Index: 6335766 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9862. Min Act: -0.1700

Data Index: 6987399 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9697. Min Act: -0.1700

Data Index: 1728527 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9613. Min Act: -0.1700

Data Index: 6321789 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9562. Min Act: -0.1700

Data Index: 1550239 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9548. Min Act: -0.1700

Data Index: 6580214 (Open Web Text)

Max Activating Token Index: 441

Text #10

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9027. Min Act: -0.1700

Data Index: 8664430 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9484. Min Act: -0.1700

Data Index: 4496027 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8865. Min Act: -0.1700

Data Index: 8799607 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9050. Min Act: -0.1700

Data Index: 5388748 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8948. Min Act: -0.1700

Data Index: 2872320 (Open Web Text)

Max Activating Token Index: 648

Text #15

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9124. Min Act: -0.1700

Data Index: 4616007 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8927. Min Act: -0.1700

Data Index: 8380276 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8934. Min Act: -0.1700

Data Index: 651463 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9048. Min Act: -0.1700

Data Index: 6888003 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8677. Min Act: -0.1700

Data Index: 3700714 (Open Web Text)

Max Activating Token Index: 272