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

Dataset: Open Web Text

Neuron 235 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: 2.9462. Min Range: -2.9462

Max Act: 2.9462. Min Act: -0.1700

Data Index: 6429856 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8969. Min Act: -0.1700

Data Index: 7169674 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8872. Min Act: -0.1700

Data Index: 6813840 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8723. Min Act: -0.1700

Data Index: 7918353 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8383. Min Act: -0.1700

Data Index: 1354165 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8366. Min Act: -0.1700

Data Index: 3380822 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8335. Min Act: -0.1700

Data Index: 7220623 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8280. Min Act: -0.1700

Data Index: 6114144 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8220. Min Act: -0.1700

Data Index: 4679658 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8286. Min Act: -0.1700

Data Index: 877066 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8265. Min Act: -0.1700

Data Index: 131461 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8172. Min Act: -0.1700

Data Index: 3451116 (Open Web Text)

Max Activating Token Index: 826

Text #12

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8292. Min Act: -0.1700

Data Index: 198687 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8045. Min Act: -0.1700

Data Index: 7269081 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8031. Min Act: -0.1700

Data Index: 2093901 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8031. Min Act: -0.1700

Data Index: 7681623 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8031. Min Act: -0.1700

Data Index: 3385953 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8004. Min Act: -0.1700

Data Index: 2764796 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8103. Min Act: -0.1700

Data Index: 464104 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 2.9462. Min Range: -2.9462

Max Act: 2.8031. Min Act: -0.1700

Data Index: 5498043 (Open Web Text)

Max Activating Token Index: 3