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

Dataset: Open Web Text

Neuron 537 in Layer 0

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: 1.9241. Min Range: -1.9241

Max Act: 1.9241. Min Act: -0.1700

Data Index: 4279011 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8385. Min Act: -0.1700

Data Index: 5495893 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8460. Min Act: -0.1700

Data Index: 238944 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8190. Min Act: -0.1700

Data Index: 4475320 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8294. Min Act: -0.1700

Data Index: 8183194 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7986. Min Act: -0.1700

Data Index: 7708787 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8016. Min Act: -0.1700

Data Index: 2095007 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8082. Min Act: -0.1700

Data Index: 7536127 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8081. Min Act: -0.1700

Data Index: 7218471 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7994. Min Act: -0.1700

Data Index: 6117201 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7848. Min Act: -0.1700

Data Index: 7413817 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7796. Min Act: -0.1700

Data Index: 7842323 (Open Web Text)

Max Activating Token Index: 876

Text #12

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7665. Min Act: -0.1700

Data Index: 5554472 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7564. Min Act: -0.1700

Data Index: 8606012 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7794. Min Act: -0.1700

Data Index: 4471348 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7781. Min Act: -0.1700

Data Index: 5900457 (Open Web Text)

Max Activating Token Index: 64

Text #16

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7572. Min Act: -0.1700

Data Index: 2976605 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7471. Min Act: -0.1700

Data Index: 1685914 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7478. Min Act: -0.1700

Data Index: 5299822 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7559. Min Act: -0.1700

Data Index: 4847136 (Open Web Text)

Max Activating Token Index: 676