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

Dataset: Open Web Text

Neuron 847 in Layer 5

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: 3.8315. Min Range: -3.8315

Max Act: 3.8098. Min Act: -0.1700

Data Index: 7781525 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.8282. Min Act: -0.1700

Data Index: 7821373 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.8315. Min Act: -0.1700

Data Index: 6345960 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7648. Min Act: -0.1700

Data Index: 8426113 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7561. Min Act: -0.1700

Data Index: 2765693 (Open Web Text)

Max Activating Token Index: 510

Text #5

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7484. Min Act: -0.1700

Data Index: 1474928 (Open Web Text)

Max Activating Token Index: 515

Text #6

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6836. Min Act: -0.1700

Data Index: 6703541 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6880. Min Act: -0.1700

Data Index: 660777 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7151. Min Act: -0.1700

Data Index: 3385220 (Open Web Text)

Max Activating Token Index: 734

Text #9

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7139. Min Act: -0.1700

Data Index: 3542688 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6675. Min Act: -0.1700

Data Index: 4357652 (Open Web Text)

Max Activating Token Index: 858

Text #11

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6768. Min Act: -0.1700

Data Index: 7933236 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6452. Min Act: -0.1700

Data Index: 6907798 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6406. Min Act: -0.1700

Data Index: 1802871 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6793. Min Act: -0.1700

Data Index: 7351627 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6697. Min Act: -0.1700

Data Index: 4598337 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6775. Min Act: -0.1700

Data Index: 4113633 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6285. Min Act: -0.1700

Data Index: 4189521 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6150. Min Act: -0.1700

Data Index: 2636724 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5734. Min Act: -0.1700

Data Index: 3717642 (Open Web Text)

Max Activating Token Index: 253