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

Dataset: Open Web Text

Neuron 2991 in Layer 3

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: 3.3644. Min Range: -3.3644

Max Act: 3.3644. Min Act: -0.1700

Data Index: 1879639 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3436. Min Act: -0.1700

Data Index: 2817372 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3241. Min Act: -0.1700

Data Index: 2163676 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3426. Min Act: -0.1700

Data Index: 7325798 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3210. Min Act: -0.1700

Data Index: 5008931 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3299. Min Act: -0.1700

Data Index: 7529515 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3306. Min Act: -0.1700

Data Index: 8551637 (Open Web Text)

Max Activating Token Index: 968

Text #7

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3282. Min Act: -0.1700

Data Index: 7093740 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3034. Min Act: -0.1700

Data Index: 2784498 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3025. Min Act: -0.1700

Data Index: 6397727 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3261. Min Act: -0.1700

Data Index: 2299864 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3006. Min Act: -0.1700

Data Index: 7151860 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2998. Min Act: -0.1700

Data Index: 1610537 (Open Web Text)

Max Activating Token Index: 571

Text #13

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.3001. Min Act: -0.1700

Data Index: 7615024 (Open Web Text)

Max Activating Token Index: 753

Text #14

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2529. Min Act: -0.1700

Data Index: 5829043 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2812. Min Act: -0.1700

Data Index: 6017139 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2651. Min Act: -0.1700

Data Index: 7093741 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2757. Min Act: -0.1700

Data Index: 2737129 (Open Web Text)

Max Activating Token Index: 906

Text #18

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2737. Min Act: -0.1700

Data Index: 6790697 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 3.3644. Min Range: -3.3644

Max Act: 3.2843. Min Act: -0.1700

Data Index: 13569 (Open Web Text)

Max Activating Token Index: 991