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

Dataset: Open Web Text

Neuron 1521 in Layer 6

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: 4.2132. Min Range: -4.2132

Max Act: 4.2132. Min Act: -0.1700

Data Index: 565682 (Open Web Text)

Max Activating Token Index: 684

Text #1

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1683. Min Act: -0.1700

Data Index: 565684 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0204. Min Act: -0.1700

Data Index: 418121 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.9167. Min Act: -0.1700

Data Index: 4702406 (Open Web Text)

Max Activating Token Index: 513

Text #4

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8876. Min Act: -0.1700

Data Index: 5755114 (Open Web Text)

Max Activating Token Index: 610

Text #5

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8501. Min Act: -0.1700

Data Index: 2119743 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8919. Min Act: -0.1700

Data Index: 4355641 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8699. Min Act: -0.1700

Data Index: 1536095 (Open Web Text)

Max Activating Token Index: 75

Text #8

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8449. Min Act: -0.1700

Data Index: 365068 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8633. Min Act: -0.1700

Data Index: 5369333 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8706. Min Act: -0.1700

Data Index: 1754771 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8563. Min Act: -0.1700

Data Index: 1832064 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8591. Min Act: -0.1700

Data Index: 3213797 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8730. Min Act: -0.1700

Data Index: 2296708 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8218. Min Act: -0.1700

Data Index: 8633905 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8441. Min Act: -0.1700

Data Index: 1645520 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8149. Min Act: -0.1700

Data Index: 2296697 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.8107. Min Act: -0.1700

Data Index: 605362 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.7752. Min Act: -0.1700

Data Index: 636840 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 4.2132. Min Range: -4.2132

Max Act: 3.7776. Min Act: -0.1700

Data Index: 6430555 (Open Web Text)

Max Activating Token Index: 506