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

Dataset: Open Web Text

Neuron 1116 in Layer 0

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: 1.3282. Min Range: -1.3282

Max Act: 1.3282. Min Act: 0.0629

Data Index: 2517133 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2929. Min Act: -0.0775

Data Index: 2073378 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2704. Min Act: -0.1012

Data Index: 7245044 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2703. Min Act: -0.0385

Data Index: 6901117 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2660. Min Act: -0.0578

Data Index: 5080736 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2609. Min Act: -0.0593

Data Index: 4543620 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2453. Min Act: -0.0825

Data Index: 5612278 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2550. Min Act: -0.0307

Data Index: 4661042 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2480. Min Act: -0.0317

Data Index: 5545949 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2463. Min Act: -0.0367

Data Index: 8437523 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2366. Min Act: -0.0389

Data Index: 6068479 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2431. Min Act: -0.0792

Data Index: 1724051 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2439. Min Act: -0.0851

Data Index: 772241 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2281. Min Act: -0.0862

Data Index: 4233740 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2272. Min Act: -0.0560

Data Index: 5484712 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2314. Min Act: -0.1279

Data Index: 475853 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2306. Min Act: -0.0705

Data Index: 3101574 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2246. Min Act: -0.0489

Data Index: 2289388 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2367. Min Act: -0.0505

Data Index: 1026326 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3282. Min Range: -1.3282

Max Act: 1.2286. Min Act: -0.0724

Data Index: 2476816 (Open Web Text)

Max Activating Token Index: 1023