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

Dataset: Open Web Text

Neuron 881 in Layer 3

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: 3.2475. Min Range: -3.2475

Max Act: 3.2475. Min Act: -0.1700

Data Index: 7175752 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2467. Min Act: -0.1700

Data Index: 4209909 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2349. Min Act: -0.1700

Data Index: 8017365 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2281. Min Act: -0.1700

Data Index: 6225876 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2084. Min Act: -0.1700

Data Index: 5364670 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2252. Min Act: -0.1700

Data Index: 4942569 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2086. Min Act: -0.1700

Data Index: 2914027 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1992. Min Act: -0.1700

Data Index: 3261879 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2090. Min Act: -0.1700

Data Index: 989234 (Open Web Text)

Max Activating Token Index: 97

Text #9

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.2018. Min Act: -0.1700

Data Index: 3889930 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1910. Min Act: -0.1700

Data Index: 2238125 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1580. Min Act: -0.1700

Data Index: 4891459 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1604. Min Act: -0.1700

Data Index: 3185547 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1581. Min Act: -0.1700

Data Index: 4209908 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1542. Min Act: -0.1700

Data Index: 3876220 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1248. Min Act: -0.1700

Data Index: 8350998 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1498247 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1128. Min Act: -0.1700

Data Index: 2463653 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1283. Min Act: -0.1700

Data Index: 5974531 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.2475. Min Range: -3.2475

Max Act: 3.1016. Min Act: -0.1700

Data Index: 6776411 (Open Web Text)

Max Activating Token Index: 942