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

Dataset: Open Web Text

Neuron 2079 in Layer 5

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: 3.8066. Min Range: -3.8066

Max Act: 3.8066. Min Act: -0.1700

Data Index: 7906174 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.7896. Min Act: -0.1700

Data Index: 1422870 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.7242. Min Act: -0.1700

Data Index: 8681961 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1380563 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.6423. Min Act: -0.1700

Data Index: 227730 (Open Web Text)

Max Activating Token Index: 783

Text #5

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.6441. Min Act: -0.1700

Data Index: 3677685 (Open Web Text)

Max Activating Token Index: 927

Text #6

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.6413. Min Act: -0.1700

Data Index: 1276117 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5771. Min Act: -0.1700

Data Index: 7104711 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5954. Min Act: -0.1700

Data Index: 581393 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5730. Min Act: -0.1700

Data Index: 5131157 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5493. Min Act: -0.1700

Data Index: 7049738 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5263. Min Act: -0.1700

Data Index: 7525798 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5482. Min Act: -0.1700

Data Index: 3560833 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5404. Min Act: -0.1700

Data Index: 5491765 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5023. Min Act: -0.1700

Data Index: 6325013 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4782. Min Act: -0.1700

Data Index: 1491678 (Open Web Text)

Max Activating Token Index: 319

Text #16

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4614. Min Act: -0.1700

Data Index: 4608328 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4433. Min Act: -0.1700

Data Index: 4368036 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4557. Min Act: -0.1700

Data Index: 1136955 (Open Web Text)

Max Activating Token Index: 845

Text #19

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4422. Min Act: -0.1700

Data Index: 3620224 (Open Web Text)

Max Activating Token Index: 990