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

Dataset: Open Web Text

Neuron 934 in Layer 0

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: 5.0534. Min Range: -5.0534

Max Act: 5.0534. Min Act: -0.1700

Data Index: 8310611 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9815. Min Act: -0.1700

Data Index: 8225439 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9828. Min Act: -0.1700

Data Index: 4550178 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9997. Min Act: -0.1700

Data Index: 6541587 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9660. Min Act: -0.1700

Data Index: 3987613 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9488. Min Act: -0.1700

Data Index: 2967600 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9485. Min Act: -0.1700

Data Index: 1877879 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9254. Min Act: -0.1700

Data Index: 3454446 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9322. Min Act: -0.1700

Data Index: 7014605 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9175. Min Act: -0.1700

Data Index: 3495931 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9338. Min Act: -0.1700

Data Index: 2364664 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9061. Min Act: -0.1700

Data Index: 3343710 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8934. Min Act: -0.1700

Data Index: 1180952 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8907. Min Act: -0.1700

Data Index: 440735 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8963. Min Act: -0.1700

Data Index: 5167368 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.9132. Min Act: -0.1700

Data Index: 2564526 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8953. Min Act: -0.1700

Data Index: 1229781 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8927. Min Act: -0.1700

Data Index: 4543134 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8972. Min Act: -0.1700

Data Index: 2106266 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 5.0534. Min Range: -5.0534

Max Act: 4.8755. Min Act: -0.1700

Data Index: 8056922 (Open Web Text)

Max Activating Token Index: 937