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

Dataset: Open Web Text

Neuron 99 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: 1.6731. Min Range: -1.6731

Max Act: 1.6731. Min Act: -0.1700

Data Index: 6025438 (Open Web Text)

Max Activating Token Index: 733

Text #1

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6593. Min Act: -0.1700

Data Index: 939814 (Open Web Text)

Max Activating Token Index: 760

Text #2

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6346. Min Act: -0.1700

Data Index: 6097670 (Open Web Text)

Max Activating Token Index: 318

Text #3

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6061. Min Act: -0.1700

Data Index: 3166043 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6119. Min Act: -0.1700

Data Index: 1126249 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6230. Min Act: -0.1700

Data Index: 6041791 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5985. Min Act: -0.1700

Data Index: 4696717 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5945. Min Act: -0.1699

Data Index: 1997856 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5954. Min Act: -0.1700

Data Index: 5198353 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5885. Min Act: -0.1700

Data Index: 2602898 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5786. Min Act: -0.1700

Data Index: 3001175 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5818. Min Act: -0.1700

Data Index: 6333583 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5881. Min Act: -0.1700

Data Index: 8709395 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5814. Min Act: -0.1700

Data Index: 6979079 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5683. Min Act: -0.1698

Data Index: 5235861 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5811. Min Act: -0.1700

Data Index: 2919100 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5655. Min Act: -0.1700

Data Index: 40524 (Open Web Text)

Max Activating Token Index: 901

Text #17

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5701. Min Act: -0.1700

Data Index: 3375482 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5730. Min Act: -0.1700

Data Index: 7772693 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5624. Min Act: -0.1700

Data Index: 7187481 (Open Web Text)

Max Activating Token Index: 828