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

Dataset: Open Web Text

Neuron 2186 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: 4.6848. Min Range: -4.6848

Max Act: 4.6848. Min Act: -0.1700

Data Index: 267317 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0988. Min Act: -0.1700

Data Index: 1626929 (Open Web Text)

Max Activating Token Index: 713

Text #2

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.1494. Min Act: -0.1700

Data Index: 7180671 (Open Web Text)

Max Activating Token Index: 822

Text #3

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0906. Min Act: -0.1700

Data Index: 1512131 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0730. Min Act: -0.1700

Data Index: 6979705 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.1047. Min Act: -0.1700

Data Index: 1494099 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0291. Min Act: -0.1700

Data Index: 5445724 (Open Web Text)

Max Activating Token Index: 711

Text #7

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.1056. Min Act: -0.1700

Data Index: 4693224 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0129. Min Act: -0.1700

Data Index: 511402 (Open Web Text)

Max Activating Token Index: 792

Text #9

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0239. Min Act: -0.1700

Data Index: 3875293 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 4.6848. Min Range: -4.6848

Max Act: 3.9661. Min Act: -0.1700

Data Index: 5445716 (Open Web Text)

Max Activating Token Index: 971

Text #11

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0121. Min Act: -0.1700

Data Index: 8278460 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0087. Min Act: -0.1700

Data Index: 8533500 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0121. Min Act: -0.1700

Data Index: 2777498 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0136. Min Act: -0.1700

Data Index: 6302642 (Open Web Text)

Max Activating Token Index: 960

Text #15

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0031. Min Act: -0.1700

Data Index: 5720885 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 4.6848. Min Range: -4.6848

Max Act: 4.0005. Min Act: -0.1700

Data Index: 3138379 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.6848. Min Range: -4.6848

Max Act: 3.9847. Min Act: -0.1700

Data Index: 8220160 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 4.6848. Min Range: -4.6848

Max Act: 3.9068. Min Act: -0.1700

Data Index: 1987842 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 4.6848. Min Range: -4.6848

Max Act: 3.9214. Min Act: -0.1700

Data Index: 2664340 (Open Web Text)

Max Activating Token Index: 74