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

Dataset: Open Web Text

Neuron 2968 in Layer 6

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: 5.1830. Min Range: -5.1830

Max Act: 5.1830. Min Act: -0.1700

Data Index: 7280420 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 5.1830. Min Range: -5.1830

Max Act: 5.1436. Min Act: -0.1700

Data Index: 3825283 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 5.1830. Min Range: -5.1830

Max Act: 5.0284. Min Act: -0.1700

Data Index: 4740354 (Open Web Text)

Max Activating Token Index: 852

Text #3

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.9652. Min Act: -0.1700

Data Index: 1414064 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.9597. Min Act: -0.1700

Data Index: 3770349 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.9374. Min Act: -0.1700

Data Index: 8289452 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8911. Min Act: -0.1700

Data Index: 7251413 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8821. Min Act: -0.1700

Data Index: 8087622 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8697. Min Act: -0.1700

Data Index: 3093583 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.9015. Min Act: -0.1700

Data Index: 5408559 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8712. Min Act: -0.1700

Data Index: 5320374 (Open Web Text)

Max Activating Token Index: 831

Text #11

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8641. Min Act: -0.1700

Data Index: 1890662 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8554. Min Act: -0.1700

Data Index: 6406707 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8217. Min Act: -0.1700

Data Index: 6270253 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8768. Min Act: -0.1700

Data Index: 8088086 (Open Web Text)

Max Activating Token Index: 881

Text #15

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8555. Min Act: -0.1700

Data Index: 4043691 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8490. Min Act: -0.1700

Data Index: 4896841 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.7936. Min Act: -0.1700

Data Index: 3214868 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8170. Min Act: -0.1700

Data Index: 1406927 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 5.1830. Min Range: -5.1830

Max Act: 4.8040. Min Act: -0.1700

Data Index: 398311 (Open Web Text)

Max Activating Token Index: 601