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

Dataset: Open Web Text

Neuron 915 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: 5.0806. Min Range: -5.0806

Max Act: 5.0806. Min Act: -0.1700

Data Index: 7529951 (Open Web Text)

Max Activating Token Index: 703

Text #1

Max Range: 5.0806. Min Range: -5.0806

Max Act: 5.0526. Min Act: -0.1700

Data Index: 7511603 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 5.0806. Min Range: -5.0806

Max Act: 5.0380. Min Act: -0.1700

Data Index: 5156063 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 5.0806. Min Range: -5.0806

Max Act: 5.0573. Min Act: -0.1700

Data Index: 4662808 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 5.0806. Min Range: -5.0806

Max Act: 5.0354. Min Act: -0.1700

Data Index: 7722671 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9851. Min Act: -0.1700

Data Index: 5510013 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9849. Min Act: -0.1700

Data Index: 1227698 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9387. Min Act: -0.1700

Data Index: 1632787 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9818. Min Act: -0.1700

Data Index: 3627972 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8987. Min Act: -0.1700

Data Index: 4088424 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9256. Min Act: -0.1700

Data Index: 6364389 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8926. Min Act: -0.1700

Data Index: 5071698 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8991. Min Act: -0.1700

Data Index: 8069941 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8818. Min Act: -0.1700

Data Index: 3015435 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9016. Min Act: -0.1700

Data Index: 7539841 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8682. Min Act: -0.1700

Data Index: 5948641 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8742. Min Act: -0.1700

Data Index: 4559215 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.9029. Min Act: -0.1700

Data Index: 2255871 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8823. Min Act: -0.1700

Data Index: 2157422 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 5.0806. Min Range: -5.0806

Max Act: 4.8642. Min Act: -0.1700

Data Index: 7362253 (Open Web Text)

Max Activating Token Index: 306