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

Dataset: Open Web Text

Neuron 59 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: 4.9989. Min Range: -4.9989

Max Act: 4.9489. Min Act: -0.1700

Data Index: 3174429 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9989. Min Act: -0.1700

Data Index: 5841059 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9097. Min Act: -0.1700

Data Index: 318468 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9215. Min Act: -0.1700

Data Index: 1724787 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9294. Min Act: -0.1700

Data Index: 2599858 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9205. Min Act: -0.1700

Data Index: 7559977 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8850. Min Act: -0.1700

Data Index: 6243799 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9145. Min Act: -0.1700

Data Index: 8575247 (Open Web Text)

Max Activating Token Index: 217

Text #8

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8793. Min Act: -0.1700

Data Index: 1199841 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9333. Min Act: -0.1700

Data Index: 3494323 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8771. Min Act: -0.1700

Data Index: 7604802 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8313. Min Act: -0.1700

Data Index: 3810442 (Open Web Text)

Max Activating Token Index: 696

Text #12

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8852. Min Act: -0.1700

Data Index: 7071322 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8858. Min Act: -0.1700

Data Index: 8329298 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.9119. Min Act: -0.1700

Data Index: 2510131 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8857. Min Act: -0.1700

Data Index: 7514882 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.7900. Min Act: -0.1700

Data Index: 7016451 (Open Web Text)

Max Activating Token Index: 913

Text #17

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8684. Min Act: -0.1700

Data Index: 3522881 (Open Web Text)

Max Activating Token Index: 161

Text #18

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8711. Min Act: -0.1700

Data Index: 104072 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 4.9989. Min Range: -4.9989

Max Act: 4.8727. Min Act: -0.1699

Data Index: 3582105 (Open Web Text)

Max Activating Token Index: 297