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

Dataset: Open Web Text

Neuron 486 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: 1.7743. Min Range: -1.7743

Max Act: 1.7743. Min Act: -0.1700

Data Index: 5695865 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6666. Min Act: -0.1700

Data Index: 2781419 (Open Web Text)

Max Activating Token Index: 858

Text #2

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6896. Min Act: -0.1700

Data Index: 5487247 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6689. Min Act: -0.1700

Data Index: 1834637 (Open Web Text)

Max Activating Token Index: 402

Text #4

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6709. Min Act: -0.1700

Data Index: 2990416 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6116. Min Act: -0.1700

Data Index: 4525137 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5797. Min Act: -0.1700

Data Index: 659203 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6041. Min Act: -0.1700

Data Index: 6491935 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5861. Min Act: -0.1700

Data Index: 557283 (Open Web Text)

Max Activating Token Index: 854

Text #9

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5583. Min Act: -0.1700

Data Index: 228678 (Open Web Text)

Max Activating Token Index: 253

Text #10

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5306. Min Act: -0.1700

Data Index: 8807424 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5246. Min Act: -0.1700

Data Index: 5812444 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5058. Min Act: -0.1700

Data Index: 4658313 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5289. Min Act: -0.1700

Data Index: 1558801 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5048. Min Act: -0.1700

Data Index: 886558 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5084. Min Act: -0.1700

Data Index: 1907121 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5012. Min Act: -0.1700

Data Index: 7617350 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5103. Min Act: -0.1700

Data Index: 3225498 (Open Web Text)

Max Activating Token Index: 629

Text #18

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4943. Min Act: -0.1700

Data Index: 1822665 (Open Web Text)

Max Activating Token Index: 95

Text #19

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4881. Min Act: -0.1700

Data Index: 4341717 (Open Web Text)

Max Activating Token Index: 883