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

Dataset: Open Web Text

Neuron 1219 in Layer 4

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: 4.3851. Min Range: -4.3851

Max Act: 4.3809. Min Act: -0.1700

Data Index: 367620 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3851. Min Act: -0.1700

Data Index: 359461 (Open Web Text)

Max Activating Token Index: 240

Text #2

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3432. Min Act: -0.1700

Data Index: 60603 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3771. Min Act: -0.1700

Data Index: 6362146 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3382. Min Act: -0.1700

Data Index: 862026 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3356. Min Act: -0.1700

Data Index: 4755311 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3475. Min Act: -0.1700

Data Index: 756389 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3261. Min Act: -0.1700

Data Index: 5774120 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2880. Min Act: -0.1700

Data Index: 8736896 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3194. Min Act: -0.1700

Data Index: 4279111 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3236. Min Act: -0.1700

Data Index: 3744448 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2822. Min Act: -0.1700

Data Index: 1804696 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2732. Min Act: -0.1700

Data Index: 6370797 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2746. Min Act: -0.1700

Data Index: 5344291 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2763. Min Act: -0.1700

Data Index: 7287650 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2850. Min Act: -0.1700

Data Index: 7390664 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2846. Min Act: -0.1700

Data Index: 8610219 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2919. Min Act: -0.1700

Data Index: 2020274 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.3087. Min Act: -0.1700

Data Index: 3213287 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 4.3851. Min Range: -4.3851

Max Act: 4.2458. Min Act: -0.1700

Data Index: 5433842 (Open Web Text)

Max Activating Token Index: 212