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

Dataset: Open Web Text

Neuron 2493 in Layer 5

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: 4.4577. Min Range: -4.4577

Max Act: 4.4577. Min Act: -0.1700

Data Index: 718502 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.3596. Min Act: -0.1700

Data Index: 2064979 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2834. Min Act: -0.1700

Data Index: 413406 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2916. Min Act: -0.1700

Data Index: 1805322 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2699. Min Act: -0.1700

Data Index: 4742258 (Open Web Text)

Max Activating Token Index: 230

Text #5

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2384. Min Act: -0.1700

Data Index: 105025 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1912. Min Act: -0.1700

Data Index: 4271502 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1922. Min Act: -0.1700

Data Index: 5059719 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1830. Min Act: -0.1700

Data Index: 8352528 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2019. Min Act: -0.1700

Data Index: 1351601 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2015. Min Act: -0.1700

Data Index: 7320920 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2040. Min Act: -0.1700

Data Index: 6604778 (Open Web Text)

Max Activating Token Index: 541

Text #12

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1972. Min Act: -0.1700

Data Index: 3790973 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7429404 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1693. Min Act: -0.1700

Data Index: 8267585 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.2158. Min Act: -0.1700

Data Index: 4913232 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1209. Min Act: -0.1700

Data Index: 7342329 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1244. Min Act: -0.1700

Data Index: 4920872 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1775. Min Act: -0.1700

Data Index: 7743516 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 4.4577. Min Range: -4.4577

Max Act: 4.1044. Min Act: -0.1700

Data Index: 2430098 (Open Web Text)

Max Activating Token Index: 23