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

Dataset: Open Web Text

Neuron 2827 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: 4.8503. Min Range: -4.8503

Max Act: 4.8503. Min Act: -0.1700

Data Index: 2271119 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.7896. Min Act: -0.1700

Data Index: 540847 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.6566. Min Act: -0.1700

Data Index: 1441088 (Open Web Text)

Max Activating Token Index: 861

Text #3

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5925. Min Act: -0.1700

Data Index: 3932403 (Open Web Text)

Max Activating Token Index: 959

Text #4

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.6118. Min Act: -0.1700

Data Index: 7249251 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5809. Min Act: -0.1700

Data Index: 1700709 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5787. Min Act: -0.1700

Data Index: 3020348 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5834. Min Act: -0.1700

Data Index: 1392931 (Open Web Text)

Max Activating Token Index: 706

Text #8

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5268. Min Act: -0.1700

Data Index: 7668470 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5693. Min Act: -0.1700

Data Index: 2426817 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5233. Min Act: -0.1700

Data Index: 1600151 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5022. Min Act: -0.1700

Data Index: 1847884 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5161. Min Act: -0.1700

Data Index: 1938166 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5275. Min Act: -0.1700

Data Index: 1395487 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5341. Min Act: -0.1700

Data Index: 8344392 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.4980. Min Act: -0.1700

Data Index: 4519923 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5109. Min Act: -0.1700

Data Index: 6120801 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5001. Min Act: -0.1700

Data Index: 2772080 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.5184. Min Act: -0.1700

Data Index: 6061407 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 4.8503. Min Range: -4.8503

Max Act: 4.4913. Min Act: -0.1700

Data Index: 3854163 (Open Web Text)

Max Activating Token Index: 197