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

Dataset: Open Web Text

Neuron 2598 in Layer 3

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: 3.1904. Min Range: -3.1904

Max Act: 3.1904. Min Act: -0.1700

Data Index: 6929145 (Open Web Text)

Max Activating Token Index: 194

Text #1

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0129. Min Act: -0.1700

Data Index: 4790772 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0776. Min Act: -0.1700

Data Index: 811365 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0456. Min Act: -0.1700

Data Index: 1257350 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0446. Min Act: -0.1700

Data Index: 5648695 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9425. Min Act: -0.1700

Data Index: 2447855 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0136. Min Act: -0.1700

Data Index: 8653795 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9630. Min Act: -0.1700

Data Index: 4927987 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0062. Min Act: -0.1700

Data Index: 4987791 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9228. Min Act: -0.1700

Data Index: 6534843 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0720. Min Act: -0.1700

Data Index: 7022179 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9254. Min Act: -0.1700

Data Index: 6998014 (Open Web Text)

Max Activating Token Index: 692

Text #12

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9661. Min Act: -0.1700

Data Index: 3552235 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0909. Min Act: -0.1700

Data Index: 160793 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0143. Min Act: -0.1700

Data Index: 8628396 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9071. Min Act: -0.1700

Data Index: 5874624 (Open Web Text)

Max Activating Token Index: 582

Text #16

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.0195. Min Act: -0.1700

Data Index: 6937913 (Open Web Text)

Max Activating Token Index: 137

Text #17

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.8681. Min Act: -0.1700

Data Index: 2875081 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9417. Min Act: -0.1700

Data Index: 4313717 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.9501. Min Act: -0.1700

Data Index: 2511309 (Open Web Text)

Max Activating Token Index: 49