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

Dataset: Open Web Text

Neuron 1679 in Layer 1

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: 1.9062. Min Range: -1.9062

Max Act: 1.9062. Min Act: -0.1700

Data Index: 1567376 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7712. Min Act: -0.1700

Data Index: 1823778 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7711. Min Act: -0.1700

Data Index: 4509032 (Open Web Text)

Max Activating Token Index: 624

Text #3

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7581. Min Act: -0.1689

Data Index: 6308857 (Open Web Text)

Max Activating Token Index: 469

Text #4

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7511. Min Act: -0.1700

Data Index: 7980348 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7339. Min Act: -0.1700

Data Index: 6308859 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7126. Min Act: -0.1700

Data Index: 1716824 (Open Web Text)

Max Activating Token Index: 104

Text #7

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7162. Min Act: -0.1700

Data Index: 4484469 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7149. Min Act: -0.1700

Data Index: 1793720 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7076. Min Act: -0.1700

Data Index: 2322724 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7034. Min Act: -0.1700

Data Index: 654116 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7011. Min Act: -0.1700

Data Index: 88240 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6991. Min Act: -0.1700

Data Index: 1823781 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.7054. Min Act: -0.1700

Data Index: 4320274 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6902. Min Act: -0.1700

Data Index: 5665161 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6850. Min Act: -0.1700

Data Index: 3533128 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6870. Min Act: -0.1700

Data Index: 442494 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6842. Min Act: -0.1700

Data Index: 6927335 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6743. Min Act: -0.1700

Data Index: 6250454 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 1.9062. Min Range: -1.9062

Max Act: 1.6732. Min Act: -0.1700

Data Index: 4599960 (Open Web Text)

Max Activating Token Index: 466