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

Dataset: Open Web Text

Neuron 2064 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: 1.9836. Min Range: -1.9836

Max Act: 1.9836. Min Act: -0.1700

Data Index: 6748418 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9827. Min Act: -0.1700

Data Index: 6404584 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9551. Min Act: -0.1700

Data Index: 6059413 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9470. Min Act: -0.1700

Data Index: 4317037 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9408. Min Act: -0.1700

Data Index: 7583853 (Open Web Text)

Max Activating Token Index: 368

Text #5

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9489. Min Act: -0.1700

Data Index: 7040746 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9510. Min Act: -0.1700

Data Index: 4927410 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9138. Min Act: -0.1700

Data Index: 217595 (Open Web Text)

Max Activating Token Index: 226

Text #8

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9301. Min Act: -0.1700

Data Index: 4084632 (Open Web Text)

Max Activating Token Index: 626

Text #9

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9332. Min Act: -0.1700

Data Index: 3127555 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9304. Min Act: -0.1700

Data Index: 3254588 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9340. Min Act: -0.1700

Data Index: 3745248 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9015. Min Act: -0.1700

Data Index: 6354529 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9022. Min Act: -0.1700

Data Index: 2785063 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8862. Min Act: -0.1700

Data Index: 4465290 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8830. Min Act: -0.1700

Data Index: 1342943 (Open Web Text)

Max Activating Token Index: 371

Text #16

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8854. Min Act: -0.1700

Data Index: 7846631 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8959. Min Act: -0.1700

Data Index: 5929018 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8780. Min Act: -0.1700

Data Index: 1620283 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8909. Min Act: -0.1700

Data Index: 573962 (Open Web Text)

Max Activating Token Index: 476