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

Dataset: Open Web Text

Neuron 2490 in Layer 1

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: 4.8741. Min Range: -4.8741

Max Act: 4.8741. Min Act: -0.1700

Data Index: 5362755 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6225. Min Act: -0.1700

Data Index: 5362752 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.5668. Min Act: -0.1700

Data Index: 2109315 (Open Web Text)

Max Activating Token Index: 193

Text #3

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.5253. Min Act: -0.1700

Data Index: 8316877 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4762. Min Act: -0.1700

Data Index: 8068926 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4915. Min Act: -0.1700

Data Index: 5362754 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4575. Min Act: -0.1700

Data Index: 2109321 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4885. Min Act: -0.1700

Data Index: 2109319 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4440. Min Act: -0.1700

Data Index: 5726517 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4571. Min Act: -0.1700

Data Index: 5726521 (Open Web Text)

Max Activating Token Index: 173

Text #10

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4524. Min Act: -0.1700

Data Index: 3480280 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4445. Min Act: -0.1700

Data Index: 8538318 (Open Web Text)

Max Activating Token Index: 169

Text #12

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4344. Min Act: -0.1700

Data Index: 8316884 (Open Web Text)

Max Activating Token Index: 56

Text #13

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4238. Min Act: -0.1700

Data Index: 693915 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4178. Min Act: -0.1700

Data Index: 2109317 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4235. Min Act: -0.1700

Data Index: 693896 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4479. Min Act: -0.1700

Data Index: 7271403 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4400. Min Act: -0.1700

Data Index: 1153936 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4071. Min Act: -0.1700

Data Index: 348357 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.4168. Min Act: -0.1700

Data Index: 1343719 (Open Web Text)

Max Activating Token Index: 295