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

Dataset: Open Web Text

Neuron 1834 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: 3.9104. Min Range: -3.9104

Max Act: 3.9104. Min Act: -0.1700

Data Index: 2248267 (Open Web Text)

Max Activating Token Index: 758

Text #1

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8645. Min Act: -0.1700

Data Index: 7223587 (Open Web Text)

Max Activating Token Index: 213

Text #2

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8555. Min Act: -0.1700

Data Index: 158942 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8579. Min Act: -0.1700

Data Index: 2921759 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8414. Min Act: -0.1700

Data Index: 3460971 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8643. Min Act: -0.1700

Data Index: 1368089 (Open Web Text)

Max Activating Token Index: 687

Text #6

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8676. Min Act: -0.1700

Data Index: 7719266 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8682. Min Act: -0.1700

Data Index: 1441111 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8289. Min Act: -0.1700

Data Index: 6907086 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8075. Min Act: -0.1700

Data Index: 241266 (Open Web Text)

Max Activating Token Index: 804

Text #10

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8251. Min Act: -0.1700

Data Index: 364525 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8290. Min Act: -0.1700

Data Index: 208050 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8058. Min Act: -0.1700

Data Index: 5955149 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8076. Min Act: -0.1700

Data Index: 6406037 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7970. Min Act: -0.1700

Data Index: 5978332 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8110. Min Act: -0.1700

Data Index: 1575123 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7786. Min Act: -0.1700

Data Index: 5668126 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7821. Min Act: -0.1700

Data Index: 4999690 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.8107. Min Act: -0.1700

Data Index: 3962132 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7984. Min Act: -0.1700

Data Index: 3656454 (Open Web Text)

Max Activating Token Index: 491