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

Dataset: Open Web Text

Neuron 544 in Layer 1

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: 2.2510. Min Range: -2.2510

Max Act: 2.2510. Min Act: -0.1700

Data Index: 2534378 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.2284. Min Act: -0.1700

Data Index: 5202657 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1776. Min Act: -0.1700

Data Index: 8353527 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1351. Min Act: -0.1700

Data Index: 4149129 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1552. Min Act: -0.1700

Data Index: 2779021 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1611. Min Act: -0.1700

Data Index: 3903059 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1517. Min Act: -0.1700

Data Index: 7152602 (Open Web Text)

Max Activating Token Index: 316

Text #7

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1528. Min Act: -0.1700

Data Index: 1980067 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1641. Min Act: -0.1700

Data Index: 7098631 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1343. Min Act: -0.1700

Data Index: 1565063 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1315. Min Act: -0.1700

Data Index: 7498070 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1414. Min Act: -0.1700

Data Index: 4805615 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1281. Min Act: -0.1700

Data Index: 441348 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1500. Min Act: -0.1700

Data Index: 7862793 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1155. Min Act: -0.1700

Data Index: 1135652 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1309. Min Act: -0.1700

Data Index: 1172124 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1173. Min Act: -0.1700

Data Index: 3494422 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1190. Min Act: -0.1700

Data Index: 6605740 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1273. Min Act: -0.1700

Data Index: 4778741 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 2.2510. Min Range: -2.2510

Max Act: 2.1118. Min Act: -0.1700

Data Index: 5957412 (Open Web Text)

Max Activating Token Index: 579