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

Dataset: Open Web Text

Neuron 615 in Layer 1

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: 0.1808. Min Range: -0.1808

Max Act: 0.1808. Min Act: -0.1694

Data Index: 2868622 (Open Web Text)

Max Activating Token Index: 752

Text #1

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1659. Min Act: -0.1700

Data Index: 8234433 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1585. Min Act: -0.1699

Data Index: 878238 (Open Web Text)

Max Activating Token Index: 710

Text #3

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1628. Min Act: -0.1700

Data Index: 2356340 (Open Web Text)

Max Activating Token Index: 722

Text #4

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1598. Min Act: -0.1700

Data Index: 6053344 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1528. Min Act: -0.1698

Data Index: 8065709 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1462. Min Act: -0.1698

Data Index: 1507318 (Open Web Text)

Max Activating Token Index: 297

Text #7

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1381. Min Act: -0.1700

Data Index: 4073282 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1400. Min Act: -0.1697

Data Index: 7891978 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1407. Min Act: -0.1700

Data Index: 3155626 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1364. Min Act: -0.1700

Data Index: 3010871 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1360. Min Act: -0.1683

Data Index: 2235259 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1358. Min Act: -0.1690

Data Index: 7449939 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1354. Min Act: -0.1700

Data Index: 7438105 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1349. Min Act: -0.1685

Data Index: 7722122 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1360. Min Act: -0.1688

Data Index: 4139278 (Open Web Text)

Max Activating Token Index: 947

Text #16

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1326. Min Act: -0.1698

Data Index: 7951236 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1308. Min Act: -0.1695

Data Index: 40740 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1311. Min Act: -0.1684

Data Index: 3996290 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1314. Min Act: -0.1700

Data Index: 6424006 (Open Web Text)

Max Activating Token Index: 1011