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

Dataset: Open Web Text

Neuron 1044 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: 3.4755. Min Range: -3.4755

Max Act: 3.4755. Min Act: -0.1700

Data Index: 244668 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2854. Min Act: -0.1700

Data Index: 8207012 (Open Web Text)

Max Activating Token Index: 376

Text #2

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2708. Min Act: -0.1700

Data Index: 662564 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2139. Min Act: -0.1700

Data Index: 6543305 (Open Web Text)

Max Activating Token Index: 781

Text #4

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2336. Min Act: -0.1700

Data Index: 5181143 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1979. Min Act: -0.1700

Data Index: 676668 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1960. Min Act: -0.1700

Data Index: 7340495 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2057. Min Act: -0.1700

Data Index: 7644980 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2016. Min Act: -0.1700

Data Index: 8705487 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1825. Min Act: -0.1700

Data Index: 6190252 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1592. Min Act: -0.1700

Data Index: 2426741 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2184. Min Act: -0.1700

Data Index: 440224 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1631331 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1771. Min Act: -0.1700

Data Index: 2455363 (Open Web Text)

Max Activating Token Index: 687

Text #14

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1657. Min Act: -0.1700

Data Index: 6582076 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1599. Min Act: -0.1700

Data Index: 1086401 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1401. Min Act: -0.1700

Data Index: 244812 (Open Web Text)

Max Activating Token Index: 335

Text #17

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1615. Min Act: -0.1700

Data Index: 2641003 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1371. Min Act: -0.1700

Data Index: 7406863 (Open Web Text)

Max Activating Token Index: 305

Text #19

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1328. Min Act: -0.1700

Data Index: 2747952 (Open Web Text)

Max Activating Token Index: 435