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

Dataset: Open Web Text

Neuron 2915 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: 1.6758. Min Range: -1.6758

Max Act: 1.6758. Min Act: -0.1698

Data Index: 966107 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6362. Min Act: -0.1682

Data Index: 2516231 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6327. Min Act: -0.1658

Data Index: 1938785 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6221. Min Act: -0.1693

Data Index: 1816134 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6130. Min Act: -0.1664

Data Index: 3603549 (Open Web Text)

Max Activating Token Index: 942

Text #5

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6095. Min Act: -0.1691

Data Index: 7015390 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6087. Min Act: -0.1700

Data Index: 1073071 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6045. Min Act: -0.1674

Data Index: 1362981 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6157. Min Act: -0.1658

Data Index: 505640 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6095. Min Act: -0.1658

Data Index: 2194646 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5957. Min Act: -0.1658

Data Index: 3308859 (Open Web Text)

Max Activating Token Index: 358

Text #11

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5835. Min Act: -0.1684

Data Index: 2348926 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5825. Min Act: -0.1658

Data Index: 1712924 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5843. Min Act: -0.1700

Data Index: 8425524 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5737. Min Act: -0.1658

Data Index: 102951 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5728. Min Act: -0.1658

Data Index: 2957471 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5761. Min Act: -0.1662

Data Index: 5727806 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5735. Min Act: -0.1658

Data Index: 700321 (Open Web Text)

Max Activating Token Index: 942

Text #18

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5730. Min Act: -0.1689

Data Index: 5914360 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.5663. Min Act: -0.1695

Data Index: 2767931 (Open Web Text)

Max Activating Token Index: 231