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

Dataset: Open Web Text

Neuron 161 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: 3.3024. Min Range: -3.3024

Max Act: 3.2991. Min Act: -0.1700

Data Index: 2785494 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.3024. Min Act: -0.1700

Data Index: 8348037 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2755. Min Act: -0.1700

Data Index: 2342351 (Open Web Text)

Max Activating Token Index: 179

Text #3

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2547. Min Act: -0.1700

Data Index: 4762348 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2192. Min Act: -0.1700

Data Index: 3321631 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2059. Min Act: -0.1700

Data Index: 7749658 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2198. Min Act: -0.1700

Data Index: 2112602 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2016. Min Act: -0.1700

Data Index: 872445 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2211. Min Act: -0.1700

Data Index: 8538121 (Open Web Text)

Max Activating Token Index: 709

Text #9

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1835. Min Act: -0.1700

Data Index: 2805769 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1811. Min Act: -0.1700

Data Index: 3602739 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1810. Min Act: -0.1700

Data Index: 3016065 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1804. Min Act: -0.1700

Data Index: 2502481 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1669. Min Act: -0.1700

Data Index: 366687 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1585. Min Act: -0.1700

Data Index: 6252789 (Open Web Text)

Max Activating Token Index: 185

Text #15

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1562. Min Act: -0.1700

Data Index: 5788429 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1425. Min Act: -0.1700

Data Index: 6788786 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1452. Min Act: -0.1700

Data Index: 5343028 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1165. Min Act: -0.1700

Data Index: 4086852 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1315. Min Act: -0.1700

Data Index: 7535012 (Open Web Text)

Max Activating Token Index: 111