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

Dataset: Open Web Text

Neuron 2519 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: 5.0602. Min Range: -5.0602

Max Act: 5.0602. Min Act: -0.1700

Data Index: 1704052 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.6153. Min Act: -0.1700

Data Index: 3076218 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5402. Min Act: -0.1700

Data Index: 81940 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5312. Min Act: -0.1700

Data Index: 7993225 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5375. Min Act: -0.1700

Data Index: 1044824 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4967. Min Act: -0.1700

Data Index: 543468 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5218. Min Act: -0.1700

Data Index: 751213 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5256. Min Act: -0.1700

Data Index: 2732599 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4825. Min Act: -0.1700

Data Index: 6068346 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4754. Min Act: -0.1700

Data Index: 1398599 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5013. Min Act: -0.1700

Data Index: 1093746 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4436. Min Act: -0.1700

Data Index: 5188978 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4603. Min Act: -0.1700

Data Index: 4582996 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4641. Min Act: -0.1700

Data Index: 8380469 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4544. Min Act: -0.1700

Data Index: 8360942 (Open Web Text)

Max Activating Token Index: 38

Text #15

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4698. Min Act: -0.1700

Data Index: 3242049 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4314. Min Act: -0.1700

Data Index: 3151357 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4278. Min Act: -0.1700

Data Index: 2955411 (Open Web Text)

Max Activating Token Index: 281

Text #18

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4418. Min Act: -0.1700

Data Index: 7214035 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4551. Min Act: -0.1700

Data Index: 2500430 (Open Web Text)

Max Activating Token Index: 255