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

Dataset: Open Web Text

Neuron 264 in Layer 5

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: 4.1043. Min Range: -4.1043

Max Act: 4.1043. Min Act: -0.1700

Data Index: 4285228 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 4.1043. Min Range: -4.1043

Max Act: 4.0217. Min Act: -0.1700

Data Index: 3151740 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 4.1043. Min Range: -4.1043

Max Act: 4.0500. Min Act: -0.1700

Data Index: 4402838 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 4.1043. Min Range: -4.1043

Max Act: 4.0008. Min Act: -0.1700

Data Index: 223259 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 4.1043. Min Range: -4.1043

Max Act: 4.0047. Min Act: -0.1700

Data Index: 6653243 (Open Web Text)

Max Activating Token Index: 956

Text #5

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9226. Min Act: -0.1700

Data Index: 3388742 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9158. Min Act: -0.1700

Data Index: 8189605 (Open Web Text)

Max Activating Token Index: 843

Text #7

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9348. Min Act: -0.1700

Data Index: 8110559 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9212. Min Act: -0.1700

Data Index: 4215370 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9349. Min Act: -0.1700

Data Index: 3046977 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9308. Min Act: -0.1700

Data Index: 3106897 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8906. Min Act: -0.1700

Data Index: 4553904 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8864. Min Act: -0.1700

Data Index: 3161535 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8973. Min Act: -0.1700

Data Index: 8098109 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9099. Min Act: -0.1700

Data Index: 7914975 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8893. Min Act: -0.1700

Data Index: 6307522 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.9186. Min Act: -0.1700

Data Index: 2942694 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8853. Min Act: -0.1700

Data Index: 5850462 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8936. Min Act: -0.1700

Data Index: 5362589 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 4.1043. Min Range: -4.1043

Max Act: 3.8828. Min Act: -0.1700

Data Index: 5255681 (Open Web Text)

Max Activating Token Index: 145