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

Dataset: Open Web Text

Neuron 377 in Layer 0

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: 3.2310. Min Range: -3.2310

Max Act: 3.2310. Min Act: -0.1700

Data Index: 6796160 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.2011. Min Act: -0.1700

Data Index: 4462284 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1545. Min Act: -0.1700

Data Index: 5578056 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1376. Min Act: -0.1700

Data Index: 6964766 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1327. Min Act: -0.1700

Data Index: 1754247 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1359. Min Act: -0.1700

Data Index: 7100407 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1045504 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1180. Min Act: -0.1700

Data Index: 3676175 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1262. Min Act: -0.1700

Data Index: 4086101 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1274. Min Act: -0.1700

Data Index: 5305034 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1377. Min Act: -0.1700

Data Index: 2234900 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1322. Min Act: -0.1700

Data Index: 6658640 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1204. Min Act: -0.1700

Data Index: 1423176 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1063. Min Act: -0.1700

Data Index: 697004 (Open Web Text)

Max Activating Token Index: 678

Text #14

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1176. Min Act: -0.1700

Data Index: 5747337 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0957. Min Act: -0.1700

Data Index: 3678648 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1120. Min Act: -0.1700

Data Index: 3717870 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1066. Min Act: -0.1700

Data Index: 3956043 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0911. Min Act: -0.1700

Data Index: 3838021 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1005. Min Act: -0.1700

Data Index: 5642768 (Open Web Text)

Max Activating Token Index: 9