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

Dataset: Open Web Text

Neuron 2919 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: 1188737 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5094. Min Act: -0.1700

Data Index: 2236923 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5012. Min Act: -0.1700

Data Index: 7268793 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4683. Min Act: -0.1700

Data Index: 8259639 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4651. Min Act: -0.1700

Data Index: 3163876 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1679446 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4193. Min Act: -0.1700

Data Index: 7029003 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4258. Min Act: -0.1700

Data Index: 7667412 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4472. Min Act: -0.1700

Data Index: 8561577 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4189. Min Act: -0.1700

Data Index: 7883521 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4245. Min Act: -0.1700

Data Index: 1501063 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3752. Min Act: -0.1700

Data Index: 6517372 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4052. Min Act: -0.1700

Data Index: 3249708 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3663. Min Act: -0.1700

Data Index: 6661189 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3672. Min Act: -0.1700

Data Index: 3454407 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4123. Min Act: -0.1700

Data Index: 2764336 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3965. Min Act: -0.1700

Data Index: 4334723 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3789. Min Act: -0.1700

Data Index: 5078370 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3598. Min Act: -0.1700

Data Index: 4009573 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3458. Min Act: -0.1700

Data Index: 7709660 (Open Web Text)

Max Activating Token Index: 555