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

Dataset: Open Web Text

Neuron 927 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: 1.8690. Min Range: -1.8690

Max Act: 1.8690. Min Act: -0.1700

Data Index: 3527248 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7865. Min Act: -0.1700

Data Index: 469434 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7855. Min Act: -0.1700

Data Index: 4646876 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7733. Min Act: -0.1700

Data Index: 7955533 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7733. Min Act: -0.1700

Data Index: 4120683 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7593. Min Act: -0.1700

Data Index: 465030 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7569. Min Act: -0.1700

Data Index: 8710676 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7612. Min Act: -0.1700

Data Index: 3334349 (Open Web Text)

Max Activating Token Index: 300

Text #8

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7477. Min Act: -0.1700

Data Index: 7046326 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7559. Min Act: -0.1700

Data Index: 3551833 (Open Web Text)

Max Activating Token Index: 709

Text #10

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7534. Min Act: -0.1700

Data Index: 5624886 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7412. Min Act: -0.1700

Data Index: 1289930 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7312. Min Act: -0.1700

Data Index: 8175117 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7257. Min Act: -0.1700

Data Index: 6831681 (Open Web Text)

Max Activating Token Index: 358

Text #14

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7298. Min Act: -0.1700

Data Index: 7774420 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7228. Min Act: -0.1700

Data Index: 2174861 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7223. Min Act: -0.1700

Data Index: 3551382 (Open Web Text)

Max Activating Token Index: 281

Text #17

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7144. Min Act: -0.1700

Data Index: 5345773 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7197. Min Act: -0.1700

Data Index: 5473397 (Open Web Text)

Max Activating Token Index: 976

Text #19

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.7186. Min Act: -0.1700

Data Index: 5494390 (Open Web Text)

Max Activating Token Index: 480