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

Dataset: Open Web Text

Neuron 509 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: 5.1822. Min Range: -5.1822

Max Act: 5.1770. Min Act: -0.1700

Data Index: 4678018 (Open Web Text)

Max Activating Token Index: 812

Text #1

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1822. Min Act: -0.1700

Data Index: 437926 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1802. Min Act: -0.1700

Data Index: 7226468 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1322. Min Act: -0.1700

Data Index: 300895 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0676. Min Act: -0.1700

Data Index: 2622682 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1806. Min Act: -0.1700

Data Index: 6981319 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1246. Min Act: -0.1700

Data Index: 6135436 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1368. Min Act: -0.1700

Data Index: 608220 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1208. Min Act: -0.1700

Data Index: 5809275 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1477. Min Act: -0.1700

Data Index: 3394254 (Open Web Text)

Max Activating Token Index: 143

Text #10

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1151. Min Act: -0.1700

Data Index: 8067821 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1048. Min Act: -0.1700

Data Index: 5896954 (Open Web Text)

Max Activating Token Index: 297

Text #12

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0448. Min Act: -0.1700

Data Index: 968138 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.1020. Min Act: -0.1700

Data Index: 1989206 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0901. Min Act: -0.1700

Data Index: 7221181 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0218. Min Act: -0.1700

Data Index: 2884526 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0365. Min Act: -0.1700

Data Index: 4875771 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0365. Min Act: -0.1700

Data Index: 2917330 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 5.1822. Min Range: -5.1822

Max Act: 5.0398. Min Act: -0.1700

Data Index: 4750574 (Open Web Text)

Max Activating Token Index: 221

Text #19

Max Range: 5.1822. Min Range: -5.1822

Max Act: 4.9800. Min Act: -0.1700

Data Index: 2884524 (Open Web Text)

Max Activating Token Index: 439