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

Dataset: Open Web Text

Neuron 2893 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: 4.8990. Min Range: -4.8990

Max Act: 4.8990. Min Act: -0.1700

Data Index: 1451344 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.7328. Min Act: -0.1700

Data Index: 1734750 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.7114. Min Act: -0.1700

Data Index: 1451345 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.6925. Min Act: -0.1700

Data Index: 3448244 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.6840. Min Act: -0.1700

Data Index: 6508356 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.6645. Min Act: -0.1700

Data Index: 1451343 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5913. Min Act: -0.1700

Data Index: 730322 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5840. Min Act: -0.1700

Data Index: 3033937 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5832. Min Act: -0.1700

Data Index: 7291525 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5901. Min Act: -0.1700

Data Index: 1950907 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.6255. Min Act: -0.1700

Data Index: 612756 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5742. Min Act: -0.1700

Data Index: 3869876 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5615. Min Act: -0.1700

Data Index: 730324 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5700. Min Act: -0.1700

Data Index: 172271 (Open Web Text)

Max Activating Token Index: 872

Text #14

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5598. Min Act: -0.1700

Data Index: 336149 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5739. Min Act: -0.1700

Data Index: 4320684 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5563. Min Act: -0.1700

Data Index: 1451340 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5107. Min Act: -0.1700

Data Index: 219613 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5227. Min Act: -0.1700

Data Index: 5823556 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 4.8990. Min Range: -4.8990

Max Act: 4.5188. Min Act: -0.1700

Data Index: 1344188 (Open Web Text)

Max Activating Token Index: 549