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

Dataset: Open Web Text

Neuron 2758 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: 1.7997. Min Range: -1.7997

Max Act: 1.7997. Min Act: -0.1619

Data Index: 5914679 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7833. Min Act: -0.1697

Data Index: 2460644 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7732. Min Act: -0.1619

Data Index: 3173261 (Open Web Text)

Max Activating Token Index: 395

Text #3

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7789. Min Act: -0.1619

Data Index: 5820302 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7767. Min Act: -0.1697

Data Index: 2334376 (Open Web Text)

Max Activating Token Index: 806

Text #5

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7663. Min Act: -0.1653

Data Index: 1428246 (Open Web Text)

Max Activating Token Index: 374

Text #6

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7671. Min Act: -0.1638

Data Index: 7743774 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7698. Min Act: -0.1619

Data Index: 3614830 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7632. Min Act: -0.1700

Data Index: 296573 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7594. Min Act: -0.1619

Data Index: 5142195 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7564. Min Act: -0.1634

Data Index: 6094392 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7563. Min Act: -0.1619

Data Index: 7926328 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7520. Min Act: -0.1619

Data Index: 8074384 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7485. Min Act: -0.1673

Data Index: 5751134 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7544. Min Act: -0.1657

Data Index: 4077169 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7456. Min Act: -0.1637

Data Index: 4993756 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7418. Min Act: -0.1681

Data Index: 5486937 (Open Web Text)

Max Activating Token Index: 363

Text #17

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7421. Min Act: -0.1619

Data Index: 5385742 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7398. Min Act: -0.1619

Data Index: 5352154 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 1.7997. Min Range: -1.7997

Max Act: 1.7320. Min Act: -0.1662

Data Index: 2540271 (Open Web Text)

Max Activating Token Index: 467