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

Dataset: Open Web Text

Neuron 809 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: 1.6406. Min Range: -1.6406

Max Act: 1.6383. Min Act: -0.1700

Data Index: 7446440 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6406. Min Act: -0.1700

Data Index: 1145682 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6237. Min Act: -0.1700

Data Index: 394502 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6314. Min Act: -0.1700

Data Index: 253006 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5977. Min Act: -0.1700

Data Index: 6689979 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6109. Min Act: -0.1700

Data Index: 8411762 (Open Web Text)

Max Activating Token Index: 513

Text #6

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6044. Min Act: -0.1700

Data Index: 3004687 (Open Web Text)

Max Activating Token Index: 360

Text #7

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6023. Min Act: -0.1700

Data Index: 634869 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5958. Min Act: -0.1700

Data Index: 7853134 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5850. Min Act: -0.1699

Data Index: 4840788 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5997. Min Act: -0.1700

Data Index: 3318208 (Open Web Text)

Max Activating Token Index: 83

Text #11

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5861. Min Act: -0.1700

Data Index: 4581092 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5790. Min Act: -0.1700

Data Index: 4650792 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5745. Min Act: -0.1700

Data Index: 4067615 (Open Web Text)

Max Activating Token Index: 829

Text #14

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5805. Min Act: -0.1700

Data Index: 3342603 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5796. Min Act: -0.1700

Data Index: 4641856 (Open Web Text)

Max Activating Token Index: 443

Text #16

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5864. Min Act: -0.1700

Data Index: 1205377 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5752. Min Act: -0.1700

Data Index: 1773525 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5767. Min Act: -0.1699

Data Index: 2232964 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5749. Min Act: -0.1700

Data Index: 1178376 (Open Web Text)

Max Activating Token Index: 417