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

Dataset: Open Web Text

Neuron 2778 in Layer 1

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: 1.8814. Min Range: -1.8814

Max Act: 1.8814. Min Act: -0.1695

Data Index: 2350407 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8624. Min Act: -0.1699

Data Index: 3245459 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8550. Min Act: -0.1700

Data Index: 5031638 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8442. Min Act: -0.1700

Data Index: 8186069 (Open Web Text)

Max Activating Token Index: 556

Text #4

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8483. Min Act: -0.1696

Data Index: 6553754 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8066. Min Act: -0.1700

Data Index: 3989634 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8113. Min Act: -0.1699

Data Index: 8631481 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7991. Min Act: -0.1691

Data Index: 6486071 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7902. Min Act: -0.1696

Data Index: 597438 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7959. Min Act: -0.1700

Data Index: 5189436 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7843. Min Act: -0.1700

Data Index: 2270650 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7775. Min Act: -0.1697

Data Index: 4911558 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7929. Min Act: -0.1700

Data Index: 969265 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7895. Min Act: -0.1697

Data Index: 1621224 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7870. Min Act: -0.1700

Data Index: 5241056 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7826. Min Act: -0.1700

Data Index: 534624 (Open Web Text)

Max Activating Token Index: 891

Text #16

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7871. Min Act: -0.1700

Data Index: 5988257 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7770. Min Act: -0.1700

Data Index: 6731038 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7738. Min Act: -0.1700

Data Index: 5498530 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7730. Min Act: -0.1700

Data Index: 6127731 (Open Web Text)

Max Activating Token Index: 241