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

Dataset: Open Web Text

Neuron 2209 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: 1.7125. Min Range: -1.7125

Max Act: 1.7125. Min Act: -0.1677

Data Index: 1944178 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6987. Min Act: -0.1700

Data Index: 1527569 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6802. Min Act: -0.1695

Data Index: 4489839 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6716. Min Act: -0.1695

Data Index: 997736 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6503. Min Act: -0.1650

Data Index: 5673419 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6506. Min Act: -0.1690

Data Index: 4138642 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6496. Min Act: -0.1700

Data Index: 781522 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6497. Min Act: -0.1484

Data Index: 3961593 (Open Web Text)

Max Activating Token Index: 685

Text #8

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6415. Min Act: -0.1692

Data Index: 5624979 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6467. Min Act: -0.1610

Data Index: 784182 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6448. Min Act: -0.1692

Data Index: 7700110 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6389. Min Act: -0.1616

Data Index: 4612744 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6380. Min Act: -0.1693

Data Index: 3579020 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6422. Min Act: -0.1621

Data Index: 4639079 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6489. Min Act: -0.1700

Data Index: 1950418 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6346. Min Act: -0.1671

Data Index: 6076797 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6341. Min Act: -0.1551

Data Index: 6132869 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6357. Min Act: -0.1655

Data Index: 4199304 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6309. Min Act: -0.1700

Data Index: 788782 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6308. Min Act: -0.1483

Data Index: 6211765 (Open Web Text)

Max Activating Token Index: 95