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

Dataset: Open Web Text

Neuron 2810 in Layer 5

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: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.1700

Data Index: 2140222 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5106. Min Act: -0.1700

Data Index: 2680219 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4985. Min Act: -0.1700

Data Index: 5693677 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4295. Min Act: -0.1700

Data Index: 2980045 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4358. Min Act: -0.1700

Data Index: 5857396 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4041. Min Act: -0.1700

Data Index: 1706004 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3747. Min Act: -0.1700

Data Index: 1935060 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3953. Min Act: -0.1700

Data Index: 4204692 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3536. Min Act: -0.1700

Data Index: 5576235 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3901. Min Act: -0.1700

Data Index: 8785257 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3557. Min Act: -0.1700

Data Index: 8661043 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3399. Min Act: -0.1700

Data Index: 5375799 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1461498 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3376. Min Act: -0.1700

Data Index: 4617544 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3287. Min Act: -0.1700

Data Index: 3765758 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3388. Min Act: -0.1700

Data Index: 463598 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3412. Min Act: -0.1700

Data Index: 782767 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3200. Min Act: -0.1700

Data Index: 5927816 (Open Web Text)

Max Activating Token Index: 936

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3350. Min Act: -0.1700

Data Index: 1793334 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3209. Min Act: -0.1700

Data Index: 1667688 (Open Web Text)

Max Activating Token Index: 1000