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

Dataset: Open Web Text

Neuron 780 in Layer 3

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: 4.4451. Min Range: -4.4451

Max Act: 4.4451. Min Act: -0.1700

Data Index: 8768112 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.1555. Min Act: -0.1700

Data Index: 8759031 (Open Web Text)

Max Activating Token Index: 971

Text #2

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.1077. Min Act: -0.1700

Data Index: 8110856 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0901. Min Act: -0.1700

Data Index: 141992 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0762. Min Act: -0.1700

Data Index: 8552395 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0625. Min Act: -0.1700

Data Index: 2360688 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0141. Min Act: -0.1700

Data Index: 802317 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0142. Min Act: -0.1700

Data Index: 7662400 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0567. Min Act: -0.1700

Data Index: 2223620 (Open Web Text)

Max Activating Token Index: 908

Text #9

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0284. Min Act: -0.1700

Data Index: 7099169 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0277. Min Act: -0.1700

Data Index: 3056204 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0383. Min Act: -0.1700

Data Index: 1204822 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0287. Min Act: -0.1700

Data Index: 4029178 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0279. Min Act: -0.1700

Data Index: 688106 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 4.4451. Min Range: -4.4451

Max Act: 3.9993. Min Act: -0.1700

Data Index: 6293972 (Open Web Text)

Max Activating Token Index: 155

Text #15

Max Range: 4.4451. Min Range: -4.4451

Max Act: 3.9877. Min Act: -0.1700

Data Index: 514902 (Open Web Text)

Max Activating Token Index: 149

Text #16

Max Range: 4.4451. Min Range: -4.4451

Max Act: 3.9524. Min Act: -0.1700

Data Index: 3208109 (Open Web Text)

Max Activating Token Index: 558

Text #17

Max Range: 4.4451. Min Range: -4.4451

Max Act: 3.9880. Min Act: -0.1700

Data Index: 3515230 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 4.4451. Min Range: -4.4451

Max Act: 3.9908. Min Act: -0.1700

Data Index: 3592817 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 4.4451. Min Range: -4.4451

Max Act: 4.0175. Min Act: -0.1700

Data Index: 3707017 (Open Web Text)

Max Activating Token Index: 570