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

Dataset: Open Web Text

Neuron 2599 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: 1.6097. Min Range: -1.6097

Max Act: 1.6087. Min Act: -0.1700

Data Index: 4071170 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5959. Min Act: -0.1700

Data Index: 2228199 (Open Web Text)

Max Activating Token Index: 715

Text #2

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.6097. Min Act: -0.1700

Data Index: 5113064 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5769. Min Act: -0.1700

Data Index: 1577231 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5763. Min Act: -0.1700

Data Index: 1733744 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5856. Min Act: -0.1700

Data Index: 687331 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5813. Min Act: -0.1700

Data Index: 3293414 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5635. Min Act: -0.1700

Data Index: 1726060 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5724. Min Act: -0.1700

Data Index: 2664759 (Open Web Text)

Max Activating Token Index: 551

Text #9

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5724. Min Act: -0.1700

Data Index: 314927 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5679. Min Act: -0.1700

Data Index: 7133244 (Open Web Text)

Max Activating Token Index: 690

Text #11

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5656. Min Act: -0.1700

Data Index: 2386182 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5702. Min Act: -0.1700

Data Index: 4552662 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5666. Min Act: -0.1700

Data Index: 3174601 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5693. Min Act: -0.1700

Data Index: 5176229 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5529. Min Act: -0.1700

Data Index: 2223961 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5675. Min Act: -0.1700

Data Index: 2999229 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5636. Min Act: -0.1700

Data Index: 6522929 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5575. Min Act: -0.1700

Data Index: 3755357 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 1.6097. Min Range: -1.6097

Max Act: 1.5498. Min Act: -0.1700

Data Index: 4692282 (Open Web Text)

Max Activating Token Index: 442