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

Dataset: Open Web Text

Neuron 1446 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: 1.3165. Min Range: -1.3165

Max Act: 1.3165. Min Act: -0.1700

Data Index: 4279679 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3010. Min Act: -0.1697

Data Index: 1202037 (Open Web Text)

Max Activating Token Index: 697

Text #2

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3134. Min Act: -0.1700

Data Index: 5363387 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3031. Min Act: -0.1700

Data Index: 5436406 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3017. Min Act: -0.1700

Data Index: 5991271 (Open Web Text)

Max Activating Token Index: 905

Text #5

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3057. Min Act: -0.1700

Data Index: 385368 (Open Web Text)

Max Activating Token Index: 687

Text #6

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.3005. Min Act: -0.1700

Data Index: 5561925 (Open Web Text)

Max Activating Token Index: 883

Text #7

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2970. Min Act: -0.1700

Data Index: 8595079 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2887. Min Act: -0.1700

Data Index: 65257 (Open Web Text)

Max Activating Token Index: 464

Text #9

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2866. Min Act: -0.1700

Data Index: 7910513 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2870. Min Act: -0.1699

Data Index: 5233510 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2849. Min Act: -0.1699

Data Index: 1409989 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2677. Min Act: -0.1700

Data Index: 7936409 (Open Web Text)

Max Activating Token Index: 182

Text #13

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2782. Min Act: -0.1699

Data Index: 731613 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2775. Min Act: -0.1700

Data Index: 7997327 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2860. Min Act: -0.1700

Data Index: 6454986 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2796. Min Act: -0.1700

Data Index: 8371395 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2742. Min Act: -0.1700

Data Index: 4884063 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2838. Min Act: -0.1700

Data Index: 1007398 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 1.3165. Min Range: -1.3165

Max Act: 1.2752. Min Act: -0.1700

Data Index: 7021516 (Open Web Text)

Max Activating Token Index: 642