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

Dataset: Open Web Text

Neuron 2926 in Layer 6

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: 6.2816. Min Range: -6.2816

Max Act: 6.2653. Min Act: -0.1700

Data Index: 802580 (Open Web Text)

Max Activating Token Index: 755

Text #1

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.2617. Min Act: -0.1700

Data Index: 2821476 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.2816. Min Act: -0.1700

Data Index: 424950 (Open Web Text)

Max Activating Token Index: 892

Text #3

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.2486. Min Act: -0.1700

Data Index: 6260910 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.2263. Min Act: -0.1700

Data Index: 8046218 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.1508. Min Act: -0.1700

Data Index: 8604460 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.1969. Min Act: -0.1700

Data Index: 7857305 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.1766. Min Act: -0.1700

Data Index: 6066102 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.1099. Min Act: -0.1700

Data Index: 7597210 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0933. Min Act: -0.1700

Data Index: 3989707 (Open Web Text)

Max Activating Token Index: 801

Text #10

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0548. Min Act: -0.1700

Data Index: 1378364 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0720. Min Act: -0.1700

Data Index: 7799754 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 6.2816. Min Range: -6.2816

Max Act: 5.9964. Min Act: -0.1700

Data Index: 7079679 (Open Web Text)

Max Activating Token Index: 900

Text #13

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0195. Min Act: -0.1700

Data Index: 3230152 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0229. Min Act: -0.1700

Data Index: 3048037 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0440. Min Act: -0.1700

Data Index: 6010263 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0712. Min Act: -0.1700

Data Index: 2801397 (Open Web Text)

Max Activating Token Index: 792

Text #17

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0495. Min Act: -0.1700

Data Index: 2072511 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 6.2816. Min Range: -6.2816

Max Act: 6.0227. Min Act: -0.1700

Data Index: 453069 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 6.2816. Min Range: -6.2816

Max Act: 5.9988. Min Act: -0.1700

Data Index: 8556609 (Open Web Text)

Max Activating Token Index: 149