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

Dataset: Open Web Text

Neuron 479 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: 4.6344. Min Range: -4.6344

Max Act: 4.6344. Min Act: -0.1700

Data Index: 3020243 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.6075. Min Act: -0.1700

Data Index: 5305061 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5879. Min Act: -0.1700

Data Index: 5801001 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5718. Min Act: -0.1700

Data Index: 6826658 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5625. Min Act: -0.1700

Data Index: 5460604 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5610. Min Act: -0.1700

Data Index: 5385477 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5347. Min Act: -0.1700

Data Index: 8414121 (Open Web Text)

Max Activating Token Index: 216

Text #7

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5276. Min Act: -0.1700

Data Index: 2674844 (Open Web Text)

Max Activating Token Index: 758

Text #8

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4819. Min Act: -0.1700

Data Index: 4486216 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4937. Min Act: -0.1700

Data Index: 1042928 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5074. Min Act: -0.1700

Data Index: 6930090 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5211. Min Act: -0.1700

Data Index: 803035 (Open Web Text)

Max Activating Token Index: 720

Text #12

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5130. Min Act: -0.1700

Data Index: 149227 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.5001. Min Act: -0.1700

Data Index: 2258790 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4825. Min Act: -0.1700

Data Index: 6086585 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4660. Min Act: -0.1700

Data Index: 5481714 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4768. Min Act: -0.1700

Data Index: 472064 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4898. Min Act: -0.1700

Data Index: 2668323 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4622. Min Act: -0.1700

Data Index: 3501593 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 4.6344. Min Range: -4.6344

Max Act: 4.4508. Min Act: -0.1700

Data Index: 3850997 (Open Web Text)

Max Activating Token Index: 175