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

Dataset: Open Web Text

Neuron 303 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: 4.5129. Min Range: -4.5129

Max Act: 4.5129. Min Act: -0.1700

Data Index: 4604156 (Open Web Text)

Max Activating Token Index: 783

Text #1

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.3002. Min Act: -0.1700

Data Index: 3208293 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.2350. Min Act: -0.1700

Data Index: 5900326 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.2420. Min Act: -0.1700

Data Index: 1824570 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.2682. Min Act: -0.1700

Data Index: 1499126 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.2433. Min Act: -0.1700

Data Index: 1445084 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.2443. Min Act: -0.1700

Data Index: 3673348 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1416. Min Act: -0.1700

Data Index: 48726 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1530. Min Act: -0.1700

Data Index: 2024171 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1675. Min Act: -0.1700

Data Index: 1806439 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1682. Min Act: -0.1700

Data Index: 6098490 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1164. Min Act: -0.1700

Data Index: 612012 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1119. Min Act: -0.1700

Data Index: 4270253 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0906. Min Act: -0.1700

Data Index: 2421921 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1095. Min Act: -0.1700

Data Index: 4321827 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0980. Min Act: -0.1700

Data Index: 5143896 (Open Web Text)

Max Activating Token Index: 860

Text #16

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.1027. Min Act: -0.1700

Data Index: 6755715 (Open Web Text)

Max Activating Token Index: 556

Text #17

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0881. Min Act: -0.1700

Data Index: 1874907 (Open Web Text)

Max Activating Token Index: 953

Text #18

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0378. Min Act: -0.1700

Data Index: 4124999 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0394. Min Act: -0.1700

Data Index: 1563027 (Open Web Text)

Max Activating Token Index: 724