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

Dataset: Open Web Text

Neuron 2211 in Layer 2

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: 6.0542. Min Range: -6.0542

Max Act: 6.0542. Min Act: -0.1699

Data Index: 5906858 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.9862. Min Act: -0.1430

Data Index: 4742642 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.9640. Min Act: -0.1674

Data Index: 28537 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.8962. Min Act: -0.0874

Data Index: 2746196 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.8465. Min Act: -0.1366

Data Index: 6648676 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.8396. Min Act: -0.1600

Data Index: 1982589 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.7703. Min Act: -0.1534

Data Index: 8653802 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.7170. Min Act: -0.1487

Data Index: 3560470 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.7346. Min Act: -0.1683

Data Index: 8484874 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.7159. Min Act: -0.1461

Data Index: 4923352 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6824. Min Act: -0.1673

Data Index: 6207942 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.7058. Min Act: -0.1685

Data Index: 1589473 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6647. Min Act: -0.1639

Data Index: 1412811 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6475. Min Act: -0.1678

Data Index: 4970910 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6800. Min Act: -0.1560

Data Index: 3377959 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6436. Min Act: -0.1695

Data Index: 6917864 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6300. Min Act: -0.0748

Data Index: 8484861 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6381. Min Act: -0.1677

Data Index: 6920475 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.6040. Min Act: -0.1698

Data Index: 2746201 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 6.0542. Min Range: -6.0542

Max Act: 5.5726. Min Act: -0.1615

Data Index: 5906852 (Open Web Text)

Max Activating Token Index: 13