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

Dataset: Open Web Text

Neuron 2513 in Layer 6

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: 4.5322. Min Range: -4.5322

Max Act: 4.5322. Min Act: -0.1700

Data Index: 2853080 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2762. Min Act: -0.1700

Data Index: 7822781 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2630. Min Act: -0.1700

Data Index: 6288654 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2457. Min Act: -0.1700

Data Index: 2933425 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2191. Min Act: -0.1700

Data Index: 3662234 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2100. Min Act: -0.1700

Data Index: 8130408 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.2226. Min Act: -0.1700

Data Index: 3770452 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1761. Min Act: -0.1700

Data Index: 1231446 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1813. Min Act: -0.1700

Data Index: 2083891 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1715. Min Act: -0.1700

Data Index: 6732782 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1848. Min Act: -0.1700

Data Index: 8032485 (Open Web Text)

Max Activating Token Index: 519

Text #11

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1435. Min Act: -0.1700

Data Index: 7314692 (Open Web Text)

Max Activating Token Index: 562

Text #12

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1464. Min Act: -0.1700

Data Index: 8143268 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1468. Min Act: -0.1700

Data Index: 4829247 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1602. Min Act: -0.1700

Data Index: 6166537 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1550. Min Act: -0.1700

Data Index: 5629691 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1821. Min Act: -0.1700

Data Index: 2624277 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1346. Min Act: -0.1700

Data Index: 7927969 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1189. Min Act: -0.1700

Data Index: 5994118 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 4.5322. Min Range: -4.5322

Max Act: 4.1202. Min Act: -0.1700

Data Index: 4887216 (Open Web Text)

Max Activating Token Index: 364