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

Dataset: Open Web Text

Neuron 311 in Layer 2

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: 4.7062. Min Range: -4.7062

Max Act: 4.7062. Min Act: -0.1700

Data Index: 6434455 (Open Web Text)

Max Activating Token Index: 708

Text #1

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.6189. Min Act: -0.1700

Data Index: 5977158 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5693. Min Act: -0.1700

Data Index: 5383936 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5721. Min Act: -0.1700

Data Index: 5666379 (Open Web Text)

Max Activating Token Index: 764

Text #4

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5710. Min Act: -0.1700

Data Index: 4675426 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5728. Min Act: -0.1700

Data Index: 1579414 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5612. Min Act: -0.1700

Data Index: 2885836 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5608. Min Act: -0.1700

Data Index: 3285872 (Open Web Text)

Max Activating Token Index: 733

Text #8

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5363. Min Act: -0.1700

Data Index: 286669 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5101. Min Act: -0.1700

Data Index: 5591416 (Open Web Text)

Max Activating Token Index: 802

Text #10

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5180. Min Act: -0.1700

Data Index: 7816037 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5045. Min Act: -0.1700

Data Index: 7134679 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5168. Min Act: -0.1700

Data Index: 367818 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5404. Min Act: -0.1700

Data Index: 7754821 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5294. Min Act: -0.1700

Data Index: 2601478 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5004. Min Act: -0.1700

Data Index: 1939025 (Open Web Text)

Max Activating Token Index: 983

Text #16

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5035. Min Act: -0.1700

Data Index: 3980209 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.4731. Min Act: -0.1700

Data Index: 6923692 (Open Web Text)

Max Activating Token Index: 854

Text #18

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.4985. Min Act: -0.1700

Data Index: 2442450 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 4.7062. Min Range: -4.7062

Max Act: 4.5117. Min Act: -0.1700

Data Index: 7638906 (Open Web Text)

Max Activating Token Index: 731