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

Dataset: Open Web Text

Neuron 1627 in Layer 4

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: 3.6498. Min Range: -3.6498

Max Act: 3.6498. Min Act: -0.1700

Data Index: 7583931 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.6314. Min Act: -0.1700

Data Index: 4773256 (Open Web Text)

Max Activating Token Index: 844

Text #2

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.6237. Min Act: -0.1700

Data Index: 3128481 (Open Web Text)

Max Activating Token Index: 737

Text #3

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5969. Min Act: -0.1700

Data Index: 3727835 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5416. Min Act: -0.1700

Data Index: 7135914 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5484. Min Act: -0.1700

Data Index: 823107 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5588. Min Act: -0.1700

Data Index: 2816664 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5489. Min Act: -0.1700

Data Index: 5920491 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5109. Min Act: -0.1700

Data Index: 1247281 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5284. Min Act: -0.1700

Data Index: 2883924 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5223. Min Act: -0.1700

Data Index: 8082353 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5306. Min Act: -0.1700

Data Index: 1972017 (Open Web Text)

Max Activating Token Index: 851

Text #12

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5274. Min Act: -0.1700

Data Index: 5898370 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4907. Min Act: -0.1700

Data Index: 7601343 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5099. Min Act: -0.1700

Data Index: 5920490 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5080. Min Act: -0.1700

Data Index: 8336703 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4767. Min Act: -0.1700

Data Index: 5582550 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4893. Min Act: -0.1700

Data Index: 776524 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4729. Min Act: -0.1700

Data Index: 6913665 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4716. Min Act: -0.1700

Data Index: 5165956 (Open Web Text)

Max Activating Token Index: 969