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

Dataset: Open Web Text

Neuron 556 in Layer 0

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: 3.6732. Min Range: -3.6732

Max Act: 3.6732. Min Act: -0.1700

Data Index: 561578 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.6046. Min Act: -0.1700

Data Index: 7826765 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5831. Min Act: -0.1700

Data Index: 8527470 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5426. Min Act: -0.1700

Data Index: 8633534 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5563. Min Act: -0.1700

Data Index: 8652399 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5472. Min Act: -0.1700

Data Index: 5223392 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5222. Min Act: -0.1700

Data Index: 6657964 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5038. Min Act: -0.1700

Data Index: 7342076 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5313. Min Act: -0.1700

Data Index: 5877630 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5081. Min Act: -0.1700

Data Index: 651032 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5300. Min Act: -0.1700

Data Index: 8789970 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5074. Min Act: -0.1700

Data Index: 3732024 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4817. Min Act: -0.1700

Data Index: 236885 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4814. Min Act: -0.1700

Data Index: 4577688 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4746. Min Act: -0.1700

Data Index: 4650790 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4763. Min Act: -0.1700

Data Index: 555859 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4858. Min Act: -0.1700

Data Index: 689154 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5034. Min Act: -0.1700

Data Index: 2475789 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4975. Min Act: -0.1700

Data Index: 5473471 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.4971. Min Act: -0.1700

Data Index: 5490850 (Open Web Text)

Max Activating Token Index: 4