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

Dataset: Open Web Text

Neuron 471 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: 3.0681. Min Range: -3.0681

Max Act: 3.0681. Min Act: -0.1700

Data Index: 1018093 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0515. Min Act: -0.1700

Data Index: 3792753 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0352. Min Act: -0.1700

Data Index: 5484527 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0438. Min Act: -0.1700

Data Index: 8738514 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0335. Min Act: -0.1700

Data Index: 6699224 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0278. Min Act: -0.1700

Data Index: 6027893 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0300. Min Act: -0.1700

Data Index: 2300407 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0344. Min Act: -0.1700

Data Index: 109155 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0299. Min Act: -0.1700

Data Index: 4248092 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0338. Min Act: -0.1700

Data Index: 5635853 (Open Web Text)

Max Activating Token Index: 134

Text #10

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0317. Min Act: -0.1700

Data Index: 2567570 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0184. Min Act: -0.1700

Data Index: 6454815 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0050. Min Act: -0.1700

Data Index: 6826457 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0164. Min Act: -0.1700

Data Index: 3375328 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0190. Min Act: -0.1700

Data Index: 4674987 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0017. Min Act: -0.1700

Data Index: 5154037 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9930. Min Act: -0.1700

Data Index: 557327 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9872. Min Act: -0.1700

Data Index: 4098262 (Open Web Text)

Max Activating Token Index: 661

Text #18

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9940. Min Act: -0.1700

Data Index: 5415715 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9975. Min Act: -0.1700

Data Index: 102879 (Open Web Text)

Max Activating Token Index: 212