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

Dataset: Open Web Text

Neuron 2531 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: 3.8439. Min Range: -3.8439

Max Act: 3.8439. Min Act: -0.1700

Data Index: 4663596 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7816. Min Act: -0.1700

Data Index: 5624142 (Open Web Text)

Max Activating Token Index: 678

Text #2

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7766. Min Act: -0.1700

Data Index: 8821693 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7467. Min Act: -0.1700

Data Index: 6711065 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7676. Min Act: -0.1700

Data Index: 3434442 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7091. Min Act: -0.1700

Data Index: 1763256 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7513. Min Act: -0.1700

Data Index: 8782944 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7132. Min Act: -0.1700

Data Index: 6906729 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7529. Min Act: -0.1700

Data Index: 1356461 (Open Web Text)

Max Activating Token Index: 472

Text #9

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7207. Min Act: -0.1700

Data Index: 2144825 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6919. Min Act: -0.1700

Data Index: 2724722 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6945. Min Act: -0.1700

Data Index: 336374 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6863. Min Act: -0.1700

Data Index: 5987060 (Open Web Text)

Max Activating Token Index: 727

Text #13

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7251. Min Act: -0.1700

Data Index: 6140645 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6834. Min Act: -0.1700

Data Index: 4299111 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6845. Min Act: -0.1700

Data Index: 2244534 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6904. Min Act: -0.1700

Data Index: 7569843 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6699. Min Act: -0.1700

Data Index: 8075181 (Open Web Text)

Max Activating Token Index: 821

Text #18

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7500. Min Act: -0.1700

Data Index: 8325933 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6599. Min Act: -0.1700

Data Index: 3703615 (Open Web Text)

Max Activating Token Index: 229