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

Dataset: Open Web Text

Neuron 476 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: 2.2728. Min Range: -2.2728

Max Act: 2.2728. Min Act: -0.1692

Data Index: 1610115 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.2565. Min Act: -0.1700

Data Index: 1745992 (Open Web Text)

Max Activating Token Index: 519

Text #2

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.2081. Min Act: -0.1692

Data Index: 8157731 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.2059. Min Act: -0.1700

Data Index: 3232268 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1870. Min Act: -0.1700

Data Index: 4684611 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1866. Min Act: -0.1698

Data Index: 4810160 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1729. Min Act: -0.1692

Data Index: 114244 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1591. Min Act: -0.1699

Data Index: 3747803 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1750. Min Act: -0.1699

Data Index: 1557634 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1703. Min Act: -0.1700

Data Index: 8702015 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1669. Min Act: -0.1700

Data Index: 328178 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1367. Min Act: -0.1692

Data Index: 3037298 (Open Web Text)

Max Activating Token Index: 992

Text #12

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1490. Min Act: -0.1700

Data Index: 604927 (Open Web Text)

Max Activating Token Index: 695

Text #13

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1530. Min Act: -0.1700

Data Index: 2857743 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1487. Min Act: -0.1700

Data Index: 6463716 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1507. Min Act: -0.1700

Data Index: 605396 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1414. Min Act: -0.1700

Data Index: 440136 (Open Web Text)

Max Activating Token Index: 394

Text #17

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1387. Min Act: -0.1700

Data Index: 191773 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1345. Min Act: -0.1700

Data Index: 402602 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 2.2728. Min Range: -2.2728

Max Act: 2.1332. Min Act: -0.1698

Data Index: 2110697 (Open Web Text)

Max Activating Token Index: 475