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

Dataset: Open Web Text

Neuron 920 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: 1.8959. Min Range: -1.8959

Max Act: 1.8959. Min Act: -0.1225

Data Index: 5966894 (Open Web Text)

Max Activating Token Index: 1

Text #1

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8959. Min Act: -0.1203

Data Index: 5966885 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8908. Min Act: -0.1570

Data Index: 4797124 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8564. Min Act: -0.1699

Data Index: 8369934 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8564. Min Act: -0.1681

Data Index: 6861798 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8564. Min Act: -0.1341

Data Index: 784650 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8564. Min Act: -0.1568

Data Index: 1272627 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8564. Min Act: -0.1591

Data Index: 4242498 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1567

Data Index: 5191875 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1681

Data Index: 5523475 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8348. Min Act: -0.1525

Data Index: 347429 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1632

Data Index: 6189867 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1533

Data Index: 587432 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1683

Data Index: 6529603 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1512

Data Index: 1765088 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1700

Data Index: 6742021 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1682

Data Index: 1045005 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1653

Data Index: 6835646 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1675

Data Index: 3802828 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.8959. Min Range: -1.8959

Max Act: 1.8385. Min Act: -0.1700

Data Index: 2346294 (Open Web Text)

Max Activating Token Index: 1