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

Dataset: Open Web Text

Neuron 2534 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: 1.7987. Min Range: -1.7987

Max Act: 1.7936. Min Act: -0.1700

Data Index: 5353765 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7987. Min Act: -0.1699

Data Index: 7210927 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7856. Min Act: -0.1700

Data Index: 812383 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7750. Min Act: -0.1700

Data Index: 1843036 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7542. Min Act: -0.1696

Data Index: 1630881 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7672. Min Act: -0.1628

Data Index: 8260162 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7442. Min Act: -0.1700

Data Index: 1477754 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7383. Min Act: -0.1700

Data Index: 1834537 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7315. Min Act: -0.1694

Data Index: 8567015 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7208. Min Act: -0.1700

Data Index: 1176468 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7178. Min Act: -0.1700

Data Index: 7382965 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7152. Min Act: -0.1700

Data Index: 7675219 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7171. Min Act: -0.1698

Data Index: 4405700 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.7057. Min Act: -0.1693

Data Index: 315477 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6959. Min Act: -0.1698

Data Index: 1606063 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6989. Min Act: -0.1699

Data Index: 5494557 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6911. Min Act: -0.1700

Data Index: 5781751 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6960. Min Act: -0.1688

Data Index: 7375102 (Open Web Text)

Max Activating Token Index: 839

Text #18

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6903. Min Act: -0.1700

Data Index: 2811674 (Open Web Text)

Max Activating Token Index: 138

Text #19

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.6927. Min Act: -0.1681

Data Index: 5685965 (Open Web Text)

Max Activating Token Index: 61