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

Dataset: Open Web Text

Neuron 1785 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: 4.7490. Min Range: -4.7490

Max Act: 4.7490. Min Act: -0.1700

Data Index: 4738432 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.6624. Min Act: -0.1700

Data Index: 5828225 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.6603. Min Act: -0.1700

Data Index: 1645379 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.6309. Min Act: -0.1700

Data Index: 269162 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.6327. Min Act: -0.1700

Data Index: 75136 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5984. Min Act: -0.1700

Data Index: 7137859 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5984. Min Act: -0.1700

Data Index: 3077977 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5849. Min Act: -0.1700

Data Index: 3492261 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5703. Min Act: -0.1700

Data Index: 7745553 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5672. Min Act: -0.1700

Data Index: 4224570 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5694. Min Act: -0.1700

Data Index: 2820625 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5536. Min Act: -0.1700

Data Index: 631543 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5563. Min Act: -0.1700

Data Index: 3514909 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5688. Min Act: -0.1700

Data Index: 7947296 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5464. Min Act: -0.1700

Data Index: 4028694 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5384. Min Act: -0.1700

Data Index: 2797581 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5244. Min Act: -0.1700

Data Index: 2734361 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5301. Min Act: -0.1700

Data Index: 5374750 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5334. Min Act: -0.1700

Data Index: 380081 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.7490. Min Range: -4.7490

Max Act: 4.5235. Min Act: -0.1700

Data Index: 4282376 (Open Web Text)

Max Activating Token Index: 6