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

Dataset: Open Web Text

Neuron 2908 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: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.1695

Data Index: 762738 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8572. Min Act: -0.1643

Data Index: 8535484 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8538. Min Act: -0.1626

Data Index: 8257137 (Open Web Text)

Max Activating Token Index: 716

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8589. Min Act: -0.1618

Data Index: 3085786 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8583. Min Act: -0.1654

Data Index: 5159464 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8433. Min Act: -0.1524

Data Index: 2519597 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8560. Min Act: -0.1637

Data Index: 2747544 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8471. Min Act: -0.1546

Data Index: 5247071 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8442. Min Act: -0.1642

Data Index: 6220850 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8456. Min Act: -0.1607

Data Index: 6033670 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8366. Min Act: -0.1660

Data Index: 7218342 (Open Web Text)

Max Activating Token Index: 319

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8349. Min Act: -0.1415

Data Index: 3408826 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8366. Min Act: -0.1693

Data Index: 4505184 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8329. Min Act: -0.1655

Data Index: 7765901 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8493. Min Act: -0.1656

Data Index: 266338 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8338. Min Act: -0.1465

Data Index: 5451938 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8285. Min Act: -0.1525

Data Index: 2355380 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8293. Min Act: -0.1576

Data Index: 5943334 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8246. Min Act: -0.1628

Data Index: 6244329 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8347. Min Act: -0.1625

Data Index: 4354549 (Open Web Text)

Max Activating Token Index: 47