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

Dataset: Open Web Text

Neuron 2121 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: 5.0218. Min Range: -5.0218

Max Act: 5.0218. Min Act: -0.1696

Data Index: 3226306 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 5.0218. Min Range: -5.0218

Max Act: 5.0001. Min Act: -0.1697

Data Index: 2240988 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.9588. Min Act: -0.1700

Data Index: 1679291 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.9020. Min Act: -0.1693

Data Index: 5669651 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.8769. Min Act: -0.1516

Data Index: 7804194 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.8647. Min Act: -0.1700

Data Index: 7552632 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.8299. Min Act: -0.1700

Data Index: 6560570 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.8307. Min Act: -0.1687

Data Index: 2240980 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7860. Min Act: -0.1700

Data Index: 130004 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.8183. Min Act: -0.1700

Data Index: 6170427 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7841. Min Act: -0.1657

Data Index: 5202160 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7310. Min Act: -0.1700

Data Index: 6839840 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7479. Min Act: -0.1700

Data Index: 1165920 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7176. Min Act: -0.1696

Data Index: 178022 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7629. Min Act: -0.1700

Data Index: 140414 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.7062. Min Act: -0.1699

Data Index: 5561850 (Open Web Text)

Max Activating Token Index: 504

Text #16

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.6671. Min Act: -0.1700

Data Index: 3390075 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.6687. Min Act: -0.1384

Data Index: 6512381 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.6402. Min Act: -0.1572

Data Index: 1165916 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 5.0218. Min Range: -5.0218

Max Act: 4.6684. Min Act: -0.1700

Data Index: 6311790 (Open Web Text)

Max Activating Token Index: 120