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

Dataset: Open Web Text

Neuron 709 in Layer 1

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: 1.8721. Min Range: -1.8721

Max Act: 1.8673. Min Act: -0.1700

Data Index: 8017374 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8721. Min Act: -0.1700

Data Index: 7924399 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8558. Min Act: -0.1700

Data Index: 1906425 (Open Web Text)

Max Activating Token Index: 44

Text #3

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8446. Min Act: -0.1698

Data Index: 27182 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8579. Min Act: -0.1700

Data Index: 2219279 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8528. Min Act: -0.1700

Data Index: 7608054 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8329. Min Act: -0.1700

Data Index: 5992334 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8410. Min Act: -0.1700

Data Index: 3253436 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8481. Min Act: -0.1700

Data Index: 2050776 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8028. Min Act: -0.1700

Data Index: 5091398 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8101. Min Act: -0.1700

Data Index: 7198520 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8228. Min Act: -0.1700

Data Index: 1633601 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8235. Min Act: -0.1700

Data Index: 3599654 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8287. Min Act: -0.1700

Data Index: 6178568 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8188. Min Act: -0.1700

Data Index: 4723357 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8113. Min Act: -0.1700

Data Index: 8791959 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.7844. Min Act: -0.1700

Data Index: 3723097 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8053. Min Act: -0.1700

Data Index: 1393180 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8002. Min Act: -0.1700

Data Index: 6596072 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8063. Min Act: -0.1700

Data Index: 7138416 (Open Web Text)

Max Activating Token Index: 32