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

Dataset: Open Web Text

Neuron 853 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: 3.4710. Min Range: -3.4710

Max Act: 3.4710. Min Act: -0.1700

Data Index: 7718210 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3352. Min Act: -0.1700

Data Index: 431216 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.2968. Min Act: -0.1700

Data Index: 8180954 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.2274. Min Act: -0.1700

Data Index: 3940255 (Open Web Text)

Max Activating Token Index: 557

Text #4

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.2537. Min Act: -0.1700

Data Index: 3574837 (Open Web Text)

Max Activating Token Index: 896

Text #5

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.2388. Min Act: -0.1700

Data Index: 7777697 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1792. Min Act: -0.1700

Data Index: 3147857 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1348. Min Act: -0.1700

Data Index: 286345 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1990. Min Act: -0.1700

Data Index: 4141353 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1290. Min Act: -0.1700

Data Index: 3800629 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1597. Min Act: -0.1700

Data Index: 2422774 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1375. Min Act: -0.1700

Data Index: 7915600 (Open Web Text)

Max Activating Token Index: 620

Text #12

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1456. Min Act: -0.1700

Data Index: 1961652 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1574. Min Act: -0.1700

Data Index: 3038679 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1156. Min Act: -0.1700

Data Index: 5673804 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1061. Min Act: -0.1700

Data Index: 6430965 (Open Web Text)

Max Activating Token Index: 418

Text #16

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.0954. Min Act: -0.1700

Data Index: 8662138 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1007. Min Act: -0.1700

Data Index: 5977046 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.1098. Min Act: -0.1700

Data Index: 7029227 (Open Web Text)

Max Activating Token Index: 841

Text #19

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.0856. Min Act: -0.1700

Data Index: 39679 (Open Web Text)

Max Activating Token Index: 150