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

Dataset: Open Web Text

Neuron 1450 in Layer 2

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: 1.6474. Min Range: -1.6474

Max Act: 1.6474. Min Act: -0.1700

Data Index: 5850256 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6349. Min Act: -0.1665

Data Index: 7595935 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5978. Min Act: -0.1700

Data Index: 8672154 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5829. Min Act: -0.1695

Data Index: 5364105 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5890. Min Act: -0.1700

Data Index: 6713334 (Open Web Text)

Max Activating Token Index: 623

Text #5

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5886. Min Act: -0.1699

Data Index: 8253984 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5809. Min Act: -0.1700

Data Index: 3842141 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5784. Min Act: -0.1672

Data Index: 7595934 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5810. Min Act: -0.1700

Data Index: 6783665 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5785. Min Act: -0.1700

Data Index: 8580278 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5767. Min Act: -0.1700

Data Index: 8422289 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5608. Min Act: -0.1700

Data Index: 7816128 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5607. Min Act: -0.1697

Data Index: 3940124 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5804. Min Act: -0.1700

Data Index: 7246025 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5515. Min Act: -0.1700

Data Index: 6326813 (Open Web Text)

Max Activating Token Index: 298

Text #15

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5657. Min Act: -0.1548

Data Index: 5898174 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5592. Min Act: -0.1700

Data Index: 1642834 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5584. Min Act: -0.1698

Data Index: 3897014 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5553. Min Act: -0.1700

Data Index: 2130744 (Open Web Text)

Max Activating Token Index: 661

Text #19

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5594. Min Act: -0.1700

Data Index: 6427766 (Open Web Text)

Max Activating Token Index: 280