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

Dataset: Open Web Text

Neuron 2167 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: 1.9655. Min Range: -1.9655

Max Act: 1.9655. Min Act: -0.1700

Data Index: 2360771 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8773. Min Act: -0.1700

Data Index: 4040111 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8614. Min Act: -0.1700

Data Index: 8384721 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8561. Min Act: -0.1700

Data Index: 3045853 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8539. Min Act: -0.1700

Data Index: 2518113 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8528. Min Act: -0.1696

Data Index: 6663913 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8554. Min Act: -0.1700

Data Index: 6250433 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8482. Min Act: -0.1700

Data Index: 5232569 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8396. Min Act: -0.1700

Data Index: 470405 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8468. Min Act: -0.1700

Data Index: 4836785 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8425. Min Act: -0.1700

Data Index: 7957830 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8433. Min Act: -0.1698

Data Index: 4195993 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8304. Min Act: -0.1700

Data Index: 1124034 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8411. Min Act: -0.1700

Data Index: 2316107 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8375. Min Act: -0.1700

Data Index: 1675441 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8268. Min Act: -0.1700

Data Index: 10709 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8231. Min Act: -0.1700

Data Index: 7967190 (Open Web Text)

Max Activating Token Index: 578

Text #17

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8274. Min Act: -0.1700

Data Index: 7752826 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8090. Min Act: -0.1700

Data Index: 2253285 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 1.9655. Min Range: -1.9655

Max Act: 1.8163. Min Act: -0.1700

Data Index: 5400097 (Open Web Text)

Max Activating Token Index: 627