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

Dataset: Open Web Text

Neuron 2861 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: 4.1794. Min Range: -4.1794

Max Act: 4.1794. Min Act: -0.1700

Data Index: 4753706 (Open Web Text)

Max Activating Token Index: 459

Text #1

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9930. Min Act: -0.1700

Data Index: 7378868 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.8831. Min Act: -0.1700

Data Index: 6399628 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.8476. Min Act: -0.1700

Data Index: 1719239 (Open Web Text)

Max Activating Token Index: 993

Text #4

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.7638. Min Act: -0.1700

Data Index: 51784 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.7084. Min Act: -0.1700

Data Index: 3551317 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.7051. Min Act: -0.1700

Data Index: 4712664 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6986. Min Act: -0.1700

Data Index: 447401 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6155. Min Act: -0.1700

Data Index: 319332 (Open Web Text)

Max Activating Token Index: 365

Text #9

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6484. Min Act: -0.1700

Data Index: 4797945 (Open Web Text)

Max Activating Token Index: 177

Text #10

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6300. Min Act: -0.1700

Data Index: 932508 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6584. Min Act: -0.1700

Data Index: 335629 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6207. Min Act: -0.1700

Data Index: 5501645 (Open Web Text)

Max Activating Token Index: 846

Text #13

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6141. Min Act: -0.1700

Data Index: 6967805 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.6116. Min Act: -0.1700

Data Index: 3288419 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.5742. Min Act: -0.1700

Data Index: 3018418 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.5501. Min Act: -0.1700

Data Index: 932498 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.5441. Min Act: -0.1700

Data Index: 2188498 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.5620. Min Act: -0.1700

Data Index: 2738620 (Open Web Text)

Max Activating Token Index: 410

Text #19

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.5473. Min Act: -0.1700

Data Index: 724218 (Open Web Text)

Max Activating Token Index: 62