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

Dataset: Open Web Text

Neuron 1505 in Layer 4

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: 3.2019. Min Range: -3.2019

Max Act: 3.2019. Min Act: -0.1700

Data Index: 3530840 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1561. Min Act: -0.1700

Data Index: 5318557 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1442. Min Act: -0.1700

Data Index: 8134624 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1697. Min Act: -0.1700

Data Index: 4942587 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1826. Min Act: -0.1700

Data Index: 5216120 (Open Web Text)

Max Activating Token Index: 367

Text #5

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1523. Min Act: -0.1700

Data Index: 3899725 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1687. Min Act: -0.1700

Data Index: 6349005 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1848948 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1405. Min Act: -0.1700

Data Index: 7033251 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1341. Min Act: -0.1700

Data Index: 5289253 (Open Web Text)

Max Activating Token Index: 858

Text #10

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1251. Min Act: -0.1700

Data Index: 3615168 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1362. Min Act: -0.1700

Data Index: 225429 (Open Web Text)

Max Activating Token Index: 696

Text #12

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.0947. Min Act: -0.1700

Data Index: 8134625 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1061. Min Act: -0.1700

Data Index: 5036375 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1033. Min Act: -0.1700

Data Index: 573742 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.1134. Min Act: -0.1700

Data Index: 8325180 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.0874. Min Act: -0.1700

Data Index: 7623668 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.0762. Min Act: -0.1700

Data Index: 5924149 (Open Web Text)

Max Activating Token Index: 166

Text #18

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.0797. Min Act: -0.1700

Data Index: 256420 (Open Web Text)

Max Activating Token Index: 948

Text #19

Max Range: 3.2019. Min Range: -3.2019

Max Act: 3.0852. Min Act: -0.1700

Data Index: 4663145 (Open Web Text)

Max Activating Token Index: 538