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

Dataset: Open Web Text

Neuron 2018 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: 4.7132. Min Range: -4.7132

Max Act: 4.7132. Min Act: -0.1700

Data Index: 4231635 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.6823. Min Act: -0.1700

Data Index: 1383019 (Open Web Text)

Max Activating Token Index: 385

Text #2

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.6483. Min Act: -0.1700

Data Index: 475008 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.6105. Min Act: -0.1700

Data Index: 6258874 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5868. Min Act: -0.1700

Data Index: 150489 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5878. Min Act: -0.1700

Data Index: 5412226 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5845. Min Act: -0.1700

Data Index: 408597 (Open Web Text)

Max Activating Token Index: 874

Text #7

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5475. Min Act: -0.1700

Data Index: 6866915 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5300. Min Act: -0.1700

Data Index: 4089827 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5065. Min Act: -0.1700

Data Index: 264968 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5207. Min Act: -0.1700

Data Index: 1506993 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5383. Min Act: -0.1700

Data Index: 3953035 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5129. Min Act: -0.1700

Data Index: 1611752 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5112. Min Act: -0.1700

Data Index: 721211 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5492. Min Act: -0.1700

Data Index: 7183523 (Open Web Text)

Max Activating Token Index: 998

Text #15

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.4944. Min Act: -0.1700

Data Index: 1653530 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5063. Min Act: -0.1700

Data Index: 5465746 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.4980. Min Act: -0.1700

Data Index: 5527291 (Open Web Text)

Max Activating Token Index: 879

Text #18

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.5034. Min Act: -0.1700

Data Index: 616018 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 4.7132. Min Range: -4.7132

Max Act: 4.4924. Min Act: -0.1700

Data Index: 1611751 (Open Web Text)

Max Activating Token Index: 30