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

Dataset: Open Web Text

Neuron 1844 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: 3.3308. Min Range: -3.3308

Max Act: 3.3308. Min Act: -0.1700

Data Index: 7039277 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.2565. Min Act: -0.1700

Data Index: 6484565 (Open Web Text)

Max Activating Token Index: 847

Text #2

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.2587. Min Act: -0.1700

Data Index: 7240266 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.2143. Min Act: -0.1700

Data Index: 1703188 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.2047. Min Act: -0.1700

Data Index: 2623542 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1977. Min Act: -0.1700

Data Index: 333178 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1730. Min Act: -0.1700

Data Index: 4691753 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1714. Min Act: -0.1700

Data Index: 5036341 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1706. Min Act: -0.1700

Data Index: 7473335 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1667. Min Act: -0.1700

Data Index: 1536201 (Open Web Text)

Max Activating Token Index: 900

Text #10

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1580. Min Act: -0.1700

Data Index: 3883053 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1438. Min Act: -0.1700

Data Index: 5566782 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1416. Min Act: -0.1700

Data Index: 5831831 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1437. Min Act: -0.1700

Data Index: 2376443 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1352. Min Act: -0.1700

Data Index: 1825478 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1266. Min Act: -0.1700

Data Index: 1328415 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1330. Min Act: -0.1700

Data Index: 7079876 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1238. Min Act: -0.1700

Data Index: 1819166 (Open Web Text)

Max Activating Token Index: 929

Text #18

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1306. Min Act: -0.1700

Data Index: 536805 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.3308. Min Range: -3.3308

Max Act: 3.1174. Min Act: -0.1700

Data Index: 2813731 (Open Web Text)

Max Activating Token Index: 200