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

Dataset: Open Web Text

Neuron 146 in Layer 3

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: 5.1800. Min Range: -5.1800

Max Act: 5.1298. Min Act: -0.1700

Data Index: 1337744 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.1800. Min Act: -0.1700

Data Index: 2537447 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.1738. Min Act: -0.1700

Data Index: 2561848 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.0939. Min Act: -0.1700

Data Index: 6220241 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.1162. Min Act: -0.1700

Data Index: 3694058 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.0250. Min Act: -0.1700

Data Index: 1221638 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9956. Min Act: -0.1700

Data Index: 6722704 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.0205. Min Act: -0.1700

Data Index: 6523243 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9368. Min Act: -0.1700

Data Index: 1090360 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9904. Min Act: -0.1700

Data Index: 4725632 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9503. Min Act: -0.1700

Data Index: 902920 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 5.1800. Min Range: -5.1800

Max Act: 5.0053. Min Act: -0.1700

Data Index: 1172055 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9415. Min Act: -0.1700

Data Index: 8344869 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.8539. Min Act: -0.1700

Data Index: 999038 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9022. Min Act: -0.1700

Data Index: 6080997 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9205. Min Act: -0.1700

Data Index: 8144622 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9224. Min Act: -0.1700

Data Index: 2100071 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.9111. Min Act: -0.1700

Data Index: 5456661 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.8622. Min Act: -0.1700

Data Index: 1122905 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.8782. Min Act: -0.1700

Data Index: 121323 (Open Web Text)

Max Activating Token Index: 348