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

Dataset: Open Web Text

Neuron 2958 in Layer 6

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: 4.8699. Min Range: -4.8699

Max Act: 4.8699. Min Act: -0.1700

Data Index: 4858879 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.8429. Min Act: -0.1700

Data Index: 2872324 (Open Web Text)

Max Activating Token Index: 273

Text #2

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7983. Min Act: -0.1700

Data Index: 1799208 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7994. Min Act: -0.1700

Data Index: 6503876 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7531. Min Act: -0.1700

Data Index: 757406 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7062. Min Act: -0.1700

Data Index: 173237 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7623. Min Act: -0.1700

Data Index: 5311412 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7189. Min Act: -0.1700

Data Index: 8663580 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.7215. Min Act: -0.1700

Data Index: 8671686 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6886. Min Act: -0.1700

Data Index: 3065974 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6911. Min Act: -0.1700

Data Index: 7251349 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6899. Min Act: -0.1700

Data Index: 1940309 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6441. Min Act: -0.1700

Data Index: 1309188 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6336. Min Act: -0.1700

Data Index: 5047628 (Open Web Text)

Max Activating Token Index: 182

Text #14

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6755. Min Act: -0.1700

Data Index: 6819639 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6221. Min Act: -0.1700

Data Index: 1900074 (Open Web Text)

Max Activating Token Index: 454

Text #16

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6169. Min Act: -0.1700

Data Index: 71565 (Open Web Text)

Max Activating Token Index: 982

Text #17

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6540. Min Act: -0.1700

Data Index: 5584345 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.6129. Min Act: -0.1700

Data Index: 751591 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 4.8699. Min Range: -4.8699

Max Act: 4.5764. Min Act: -0.1700

Data Index: 47995 (Open Web Text)

Max Activating Token Index: 884