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

Dataset: Open Web Text

Neuron 1754 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: 5.4248. Min Range: -5.4248

Max Act: 5.4248. Min Act: -0.1700

Data Index: 8021764 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.3254. Min Act: -0.1700

Data Index: 3758254 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.3167. Min Act: -0.1700

Data Index: 7871301 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.2201. Min Act: -0.1700

Data Index: 2566903 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1927. Min Act: -0.1700

Data Index: 199655 (Open Web Text)

Max Activating Token Index: 1005

Text #5

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1893. Min Act: -0.1700

Data Index: 8393720 (Open Web Text)

Max Activating Token Index: 868

Text #6

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1902. Min Act: -0.1700

Data Index: 874533 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.2315. Min Act: -0.1700

Data Index: 4671639 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1593. Min Act: -0.1700

Data Index: 3034615 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1339. Min Act: -0.1700

Data Index: 4958345 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1156. Min Act: -0.1700

Data Index: 5115600 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1649. Min Act: -0.1700

Data Index: 7764965 (Open Web Text)

Max Activating Token Index: 235

Text #12

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1215. Min Act: -0.1700

Data Index: 4226876 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1465. Min Act: -0.1700

Data Index: 5167301 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1131. Min Act: -0.1700

Data Index: 6622484 (Open Web Text)

Max Activating Token Index: 304

Text #15

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1633. Min Act: -0.1700

Data Index: 6393989 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.0972. Min Act: -0.1700

Data Index: 7125997 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1169. Min Act: -0.1700

Data Index: 271210 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1048. Min Act: -0.1700

Data Index: 4438757 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 5.4248. Min Range: -5.4248

Max Act: 5.1063. Min Act: -0.1700

Data Index: 4446725 (Open Web Text)

Max Activating Token Index: 579