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

Dataset: Open Web Text

Neuron 1960 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: 3.1680. Min Range: -3.1680

Max Act: 3.1680. Min Act: -0.1700

Data Index: 1963095 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 3.1680. Min Range: -3.1680

Max Act: 3.1094. Min Act: -0.1700

Data Index: 1736001 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.1680. Min Range: -3.1680

Max Act: 3.0963. Min Act: -0.1700

Data Index: 7324228 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9982. Min Act: -0.1700

Data Index: 1893486 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 3.1680. Min Range: -3.1680

Max Act: 3.0017. Min Act: -0.1700

Data Index: 8646853 (Open Web Text)

Max Activating Token Index: 358

Text #5

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9986. Min Act: -0.1700

Data Index: 2999388 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 3.1680. Min Range: -3.1680

Max Act: 3.0060. Min Act: -0.1700

Data Index: 5778973 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9940. Min Act: -0.1700

Data Index: 5800298 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9635. Min Act: -0.1700

Data Index: 6461779 (Open Web Text)

Max Activating Token Index: 215

Text #9

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9721. Min Act: -0.1700

Data Index: 2319231 (Open Web Text)

Max Activating Token Index: 431

Text #10

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9523. Min Act: -0.1700

Data Index: 768749 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9542. Min Act: -0.1700

Data Index: 7535929 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9566. Min Act: -0.1700

Data Index: 295879 (Open Web Text)

Max Activating Token Index: 862

Text #13

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9598. Min Act: -0.1700

Data Index: 6620696 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9502. Min Act: -0.1700

Data Index: 6728477 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9437. Min Act: -0.1700

Data Index: 8448744 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9413. Min Act: -0.1700

Data Index: 871700 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9382. Min Act: -0.1700

Data Index: 39945 (Open Web Text)

Max Activating Token Index: 712

Text #18

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9555. Min Act: -0.1700

Data Index: 933716 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 3.1680. Min Range: -3.1680

Max Act: 2.9402. Min Act: -0.1700

Data Index: 4014769 (Open Web Text)

Max Activating Token Index: 25