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

Dataset: Open Web Text

Neuron 784 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: 5.1881. Min Range: -5.1881

Max Act: 5.1881. Min Act: -0.1700

Data Index: 1484476 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 5.1881. Min Range: -5.1881

Max Act: 5.1002. Min Act: -0.1700

Data Index: 3836445 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 5.1881. Min Range: -5.1881

Max Act: 5.0288. Min Act: -0.1700

Data Index: 7554017 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 5.1881. Min Range: -5.1881

Max Act: 5.0544. Min Act: -0.1700

Data Index: 6347758 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9995. Min Act: -0.1700

Data Index: 7096646 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9987. Min Act: -0.1700

Data Index: 4685671 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 5.1881. Min Range: -5.1881

Max Act: 5.0208. Min Act: -0.1699

Data Index: 5103376 (Open Web Text)

Max Activating Token Index: 709

Text #7

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9952. Min Act: -0.1700

Data Index: 556225 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9986. Min Act: -0.1700

Data Index: 4336726 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 5.1881. Min Range: -5.1881

Max Act: 5.0348. Min Act: -0.1700

Data Index: 3448146 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9402. Min Act: -0.1700

Data Index: 2133844 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9363. Min Act: -0.1700

Data Index: 4524255 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9737. Min Act: -0.1700

Data Index: 3827697 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9414. Min Act: -0.1700

Data Index: 3756119 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9170. Min Act: -0.1700

Data Index: 1574645 (Open Web Text)

Max Activating Token Index: 771

Text #15

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9670. Min Act: -0.1700

Data Index: 3567889 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9714. Min Act: -0.1700

Data Index: 5204106 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9342. Min Act: -0.1700

Data Index: 5295610 (Open Web Text)

Max Activating Token Index: 445

Text #18

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9818. Min Act: -0.1700

Data Index: 6035012 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.9549. Min Act: -0.1700

Data Index: 6623756 (Open Web Text)

Max Activating Token Index: 562