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

Dataset: Open Web Text

Neuron 1643 in Layer 1

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: 1.3700. Min Range: -1.3700

Max Act: 1.3700. Min Act: -0.1700

Data Index: 5662660 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3613. Min Act: -0.1700

Data Index: 8635032 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3366. Min Act: -0.1700

Data Index: 4283435 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3480. Min Act: -0.1699

Data Index: 7486075 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3378. Min Act: -0.1700

Data Index: 1837455 (Open Web Text)

Max Activating Token Index: 513

Text #5

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3448. Min Act: -0.1699

Data Index: 2998010 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3209. Min Act: -0.1700

Data Index: 7686699 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3238. Min Act: -0.1700

Data Index: 7876034 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3269. Min Act: -0.1697

Data Index: 3056352 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3238. Min Act: -0.1700

Data Index: 1432144 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3190. Min Act: -0.1700

Data Index: 408656 (Open Web Text)

Max Activating Token Index: 246

Text #11

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3164. Min Act: -0.1696

Data Index: 3137890 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3106. Min Act: -0.1700

Data Index: 5795343 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3210. Min Act: -0.1700

Data Index: 4527735 (Open Web Text)

Max Activating Token Index: 599

Text #14

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3135. Min Act: -0.1700

Data Index: 2463608 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3035. Min Act: -0.1700

Data Index: 50881 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3071. Min Act: -0.1693

Data Index: 933799 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3124. Min Act: -0.1700

Data Index: 2622085 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3090. Min Act: -0.1700

Data Index: 3438420 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3107. Min Act: -0.1700

Data Index: 440579 (Open Web Text)

Max Activating Token Index: 492