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

Dataset: Open Web Text

Neuron 634 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: 1.2463. Min Range: -1.2463

Max Act: 1.2463. Min Act: -0.1700

Data Index: 4765579 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.2271. Min Act: -0.1700

Data Index: 370145 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.2029. Min Act: -0.1700

Data Index: 2710991 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.2000. Min Act: -0.1700

Data Index: 6396767 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1819. Min Act: -0.1700

Data Index: 5183126 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1822. Min Act: -0.1700

Data Index: 7777552 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1516. Min Act: -0.1700

Data Index: 4613701 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1490. Min Act: -0.1700

Data Index: 4894223 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1287. Min Act: -0.1700

Data Index: 6239757 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1353. Min Act: -0.1700

Data Index: 773598 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1426. Min Act: -0.1700

Data Index: 3910402 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1284. Min Act: -0.1700

Data Index: 7220632 (Open Web Text)

Max Activating Token Index: 50

Text #12

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1326. Min Act: -0.1700

Data Index: 1891142 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1359. Min Act: -0.1700

Data Index: 1802155 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1339. Min Act: -0.1700

Data Index: 2989036 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1222. Min Act: -0.1700

Data Index: 23697 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1252. Min Act: -0.1700

Data Index: 3170973 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1092. Min Act: -0.1700

Data Index: 5043475 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1270. Min Act: -0.1700

Data Index: 8300844 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1101. Min Act: -0.1700

Data Index: 8321619 (Open Web Text)

Max Activating Token Index: 34