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

Dataset: Open Web Text

Neuron 80 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: 5.1909. Min Range: -5.1909

Max Act: 5.1909. Min Act: -0.1700

Data Index: 901801 (Open Web Text)

Max Activating Token Index: 789

Text #1

Max Range: 5.1909. Min Range: -5.1909

Max Act: 5.1726. Min Act: -0.1700

Data Index: 2917750 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 5.1909. Min Range: -5.1909

Max Act: 5.0956. Min Act: -0.1700

Data Index: 5807081 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 5.1909. Min Range: -5.1909

Max Act: 5.0667. Min Act: -0.1700

Data Index: 4120140 (Open Web Text)

Max Activating Token Index: 853

Text #4

Max Range: 5.1909. Min Range: -5.1909

Max Act: 5.0527. Min Act: -0.1700

Data Index: 5727243 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9919. Min Act: -0.1700

Data Index: 4241864 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9975. Min Act: -0.1700

Data Index: 206345 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9750. Min Act: -0.1700

Data Index: 8455412 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9546. Min Act: -0.1700

Data Index: 4217698 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9489. Min Act: -0.1700

Data Index: 1579659 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9328. Min Act: -0.1700

Data Index: 3206617 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9321. Min Act: -0.1700

Data Index: 1559945 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9148. Min Act: -0.1700

Data Index: 6437949 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.9278. Min Act: -0.1700

Data Index: 7019810 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8516. Min Act: -0.1700

Data Index: 6517807 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8649. Min Act: -0.1700

Data Index: 8256538 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8268. Min Act: -0.1700

Data Index: 2294669 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8326. Min Act: -0.1700

Data Index: 2924469 (Open Web Text)

Max Activating Token Index: 582

Text #18

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8602. Min Act: -0.1700

Data Index: 4431110 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 5.1909. Min Range: -5.1909

Max Act: 4.8394. Min Act: -0.1700

Data Index: 5659834 (Open Web Text)

Max Activating Token Index: 805