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

Dataset: Open Web Text

Neuron 2796 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: 4.7188. Min Range: -4.7188

Max Act: 4.7188. Min Act: -0.1700

Data Index: 2773893 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6917. Min Act: -0.1700

Data Index: 4837481 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6967. Min Act: -0.1700

Data Index: 5013739 (Open Web Text)

Max Activating Token Index: 816

Text #3

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6142. Min Act: -0.1700

Data Index: 4834095 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6407. Min Act: -0.1700

Data Index: 1920573 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6351. Min Act: -0.1700

Data Index: 556066 (Open Web Text)

Max Activating Token Index: 948

Text #6

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.6035. Min Act: -0.1700

Data Index: 4003181 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5871. Min Act: -0.1700

Data Index: 2115193 (Open Web Text)

Max Activating Token Index: 778

Text #8

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5506. Min Act: -0.1700

Data Index: 7307809 (Open Web Text)

Max Activating Token Index: 173

Text #9

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5107. Min Act: -0.1700

Data Index: 5644690 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.4937. Min Act: -0.1700

Data Index: 5488945 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.4730. Min Act: -0.1700

Data Index: 7582177 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.4558. Min Act: -0.1700

Data Index: 7486324 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.4459. Min Act: -0.1700

Data Index: 3268457 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.4144. Min Act: -0.1700

Data Index: 970701 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3994. Min Act: -0.1700

Data Index: 6239146 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3622. Min Act: -0.1700

Data Index: 3094550 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3825. Min Act: -0.1700

Data Index: 332377 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3368. Min Act: -0.1700

Data Index: 5686125 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3286. Min Act: -0.1700

Data Index: 1602643 (Open Web Text)

Max Activating Token Index: 527