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

Dataset: Open Web Text

Neuron 2215 in Layer 5

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: 5.0865. Min Range: -5.0865

Max Act: 5.0865. Min Act: -0.1700

Data Index: 6677118 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9777. Min Act: -0.1700

Data Index: 6269872 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9696. Min Act: -0.1700

Data Index: 4545004 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9410. Min Act: -0.1700

Data Index: 216907 (Open Web Text)

Max Activating Token Index: 768

Text #4

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9489. Min Act: -0.1700

Data Index: 6060468 (Open Web Text)

Max Activating Token Index: 355

Text #5

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9331. Min Act: -0.1700

Data Index: 5469220 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9364. Min Act: -0.1700

Data Index: 555685 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9124. Min Act: -0.1700

Data Index: 5108148 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8881. Min Act: -0.1700

Data Index: 1639736 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.9280. Min Act: -0.1700

Data Index: 3489720 (Open Web Text)

Max Activating Token Index: 612

Text #10

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8586. Min Act: -0.1700

Data Index: 1261493 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8693. Min Act: -0.1700

Data Index: 43727 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8434. Min Act: -0.1700

Data Index: 4756817 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8343. Min Act: -0.1700

Data Index: 2603589 (Open Web Text)

Max Activating Token Index: 597

Text #14

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8391. Min Act: -0.1700

Data Index: 7500563 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8647. Min Act: -0.1700

Data Index: 2131555 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.8147. Min Act: -0.1700

Data Index: 1670212 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.7309. Min Act: -0.1700

Data Index: 3390152 (Open Web Text)

Max Activating Token Index: 876

Text #18

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.7905. Min Act: -0.1700

Data Index: 4881946 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 5.0865. Min Range: -5.0865

Max Act: 4.7743. Min Act: -0.1700

Data Index: 255007 (Open Web Text)

Max Activating Token Index: 317