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

Dataset: Open Web Text

Neuron 1241 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: 1.8828. Min Range: -1.8828

Max Act: 1.8828. Min Act: -0.1700

Data Index: 2676341 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8639. Min Act: -0.1700

Data Index: 2903949 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8515. Min Act: -0.1700

Data Index: 1311352 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8240. Min Act: -0.1700

Data Index: 6695111 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8247. Min Act: -0.1700

Data Index: 3630596 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8172. Min Act: -0.1700

Data Index: 624995 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8204. Min Act: -0.1700

Data Index: 3920705 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8142. Min Act: -0.1700

Data Index: 5318447 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7936. Min Act: -0.1700

Data Index: 7631581 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7911. Min Act: -0.1700

Data Index: 6695112 (Open Web Text)

Max Activating Token Index: 567

Text #10

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8015. Min Act: -0.1700

Data Index: 7149817 (Open Web Text)

Max Activating Token Index: 610

Text #11

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7940. Min Act: -0.1700

Data Index: 6066723 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7889. Min Act: -0.1700

Data Index: 7574860 (Open Web Text)

Max Activating Token Index: 393

Text #13

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7918. Min Act: -0.1700

Data Index: 2101736 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7848. Min Act: -0.1700

Data Index: 7097225 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7874. Min Act: -0.1700

Data Index: 5588519 (Open Web Text)

Max Activating Token Index: 204

Text #16

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7911. Min Act: -0.1700

Data Index: 3321641 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7800. Min Act: -0.1700

Data Index: 1698230 (Open Web Text)

Max Activating Token Index: 413

Text #18

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7797. Min Act: -0.1700

Data Index: 4506781 (Open Web Text)

Max Activating Token Index: 941

Text #19

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7701. Min Act: -0.1700

Data Index: 3848791 (Open Web Text)

Max Activating Token Index: 533