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

Dataset: Open Web Text

Neuron 485 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: 3.1806. Min Range: -3.1806

Max Act: 3.1806. Min Act: -0.1700

Data Index: 1169949 (Open Web Text)

Max Activating Token Index: 870

Text #1

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0630. Min Act: -0.1700

Data Index: 6070102 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0390. Min Act: -0.1700

Data Index: 2637744 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0524. Min Act: -0.1700

Data Index: 2336320 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0104. Min Act: -0.1700

Data Index: 4353537 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9910. Min Act: -0.1700

Data Index: 1700979 (Open Web Text)

Max Activating Token Index: 857

Text #6

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9899. Min Act: -0.1700

Data Index: 6070119 (Open Web Text)

Max Activating Token Index: 568

Text #7

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0126. Min Act: -0.1700

Data Index: 6395598 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9769. Min Act: -0.1700

Data Index: 2738234 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9794. Min Act: -0.1700

Data Index: 2738233 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9674. Min Act: -0.1700

Data Index: 2637748 (Open Web Text)

Max Activating Token Index: 850

Text #11

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9620. Min Act: -0.1700

Data Index: 6181082 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9991. Min Act: -0.1700

Data Index: 1640246 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9748. Min Act: -0.1700

Data Index: 6153830 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9743. Min Act: -0.1700

Data Index: 1636661 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9594. Min Act: -0.1700

Data Index: 1636701 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9684. Min Act: -0.1700

Data Index: 2637750 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9631. Min Act: -0.1700

Data Index: 8629557 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9654. Min Act: -0.1700

Data Index: 5402339 (Open Web Text)

Max Activating Token Index: 661

Text #19

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9446. Min Act: -0.1700

Data Index: 5912547 (Open Web Text)

Max Activating Token Index: 699