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

Dataset: Open Web Text

Neuron 1599 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: 4.4652. Min Range: -4.4652

Max Act: 4.4388. Min Act: -0.1700

Data Index: 840268 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4652. Min Act: -0.1700

Data Index: 6666344 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4058. Min Act: -0.1700

Data Index: 3048269 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4232. Min Act: -0.1700

Data Index: 385081 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4262. Min Act: -0.1700

Data Index: 8756221 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4138. Min Act: -0.1700

Data Index: 172145 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4176. Min Act: -0.1700

Data Index: 4894934 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4388. Min Act: -0.1700

Data Index: 4551451 (Open Web Text)

Max Activating Token Index: 758

Text #8

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4401. Min Act: -0.1700

Data Index: 4106183 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4235. Min Act: -0.1700

Data Index: 3930472 (Open Web Text)

Max Activating Token Index: 731

Text #10

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4157. Min Act: -0.1700

Data Index: 2103644 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4123. Min Act: -0.1700

Data Index: 517686 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4493. Min Act: -0.1700

Data Index: 1869384 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4078. Min Act: -0.1700

Data Index: 855729 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4126. Min Act: -0.1700

Data Index: 1823332 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.3821. Min Act: -0.1700

Data Index: 773877 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.4006. Min Act: -0.1700

Data Index: 810405 (Open Web Text)

Max Activating Token Index: 639

Text #17

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.3762. Min Act: -0.1700

Data Index: 3716199 (Open Web Text)

Max Activating Token Index: 360

Text #18

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.3845. Min Act: -0.1700

Data Index: 1579806 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 4.4652. Min Range: -4.4652

Max Act: 4.3909. Min Act: -0.1700

Data Index: 3801978 (Open Web Text)

Max Activating Token Index: 443