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

Dataset: Open Web Text

Neuron 2632 in Layer 2

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: 1.8020. Min Range: -1.8020

Max Act: 1.8020. Min Act: -0.1700

Data Index: 3067385 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.7493. Min Act: -0.1699

Data Index: 5900214 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6994. Min Act: -0.1700

Data Index: 6642956 (Open Web Text)

Max Activating Token Index: 651

Text #3

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6905. Min Act: -0.1699

Data Index: 4080294 (Open Web Text)

Max Activating Token Index: 220

Text #4

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6765. Min Act: -0.1700

Data Index: 2674160 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6648. Min Act: -0.1700

Data Index: 1829889 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6541. Min Act: -0.1699

Data Index: 6506859 (Open Web Text)

Max Activating Token Index: 204

Text #7

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6525. Min Act: -0.1700

Data Index: 8138652 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6334. Min Act: -0.1700

Data Index: 631369 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6498. Min Act: -0.1700

Data Index: 5342768 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6356. Min Act: -0.1699

Data Index: 3229964 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6338. Min Act: -0.1699

Data Index: 2072619 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6404. Min Act: -0.1700

Data Index: 1480293 (Open Web Text)

Max Activating Token Index: 698

Text #13

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6377. Min Act: -0.1700

Data Index: 1829890 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6322. Min Act: -0.1700

Data Index: 8794644 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6340. Min Act: -0.1700

Data Index: 471977 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6246. Min Act: -0.1700

Data Index: 1629728 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6235. Min Act: -0.1700

Data Index: 2215486 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6298. Min Act: -0.1700

Data Index: 6182177 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6138. Min Act: -0.1699

Data Index: 6009433 (Open Web Text)

Max Activating Token Index: 473