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

Dataset: Open Web Text

Neuron 1702 in Layer 2

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: 4.2483. Min Range: -4.2483

Max Act: 4.2483. Min Act: -0.1700

Data Index: 8554002 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.2452. Min Act: -0.1700

Data Index: 792440 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0882. Min Act: -0.1700

Data Index: 2950707 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0853. Min Act: -0.1700

Data Index: 7792708 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0870. Min Act: -0.1700

Data Index: 8362137 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0587. Min Act: -0.1700

Data Index: 4616915 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0380. Min Act: -0.1700

Data Index: 7574329 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9853. Min Act: -0.1700

Data Index: 1564987 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.0030. Min Act: -0.1700

Data Index: 8149628 (Open Web Text)

Max Activating Token Index: 716

Text #9

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9987. Min Act: -0.1700

Data Index: 5119516 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9436. Min Act: -0.1700

Data Index: 5750261 (Open Web Text)

Max Activating Token Index: 922

Text #11

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9493. Min Act: -0.1700

Data Index: 2687589 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9684. Min Act: -0.1700

Data Index: 6909759 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9784. Min Act: -0.1700

Data Index: 8028837 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9820. Min Act: -0.1700

Data Index: 6536364 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9717. Min Act: -0.1700

Data Index: 6095645 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9705. Min Act: -0.1700

Data Index: 8236683 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9474. Min Act: -0.1700

Data Index: 7147623 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9139. Min Act: -0.1700

Data Index: 2843795 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9331. Min Act: -0.1700

Data Index: 5268484 (Open Web Text)

Max Activating Token Index: 154