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

Dataset: Open Web Text

Neuron 1435 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: 4.9005. Min Range: -4.9005

Max Act: 4.9005. Min Act: -0.1700

Data Index: 8065010 (Open Web Text)

Max Activating Token Index: 901

Text #1

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.8433. Min Act: -0.1700

Data Index: 7525341 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.8319. Min Act: -0.1700

Data Index: 2945345 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7127. Min Act: -0.1700

Data Index: 2111723 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7451. Min Act: -0.1700

Data Index: 5536017 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7430. Min Act: -0.1700

Data Index: 761649 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7525. Min Act: -0.1700

Data Index: 2158287 (Open Web Text)

Max Activating Token Index: 449

Text #7

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7377. Min Act: -0.1700

Data Index: 5367764 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.7093. Min Act: -0.1700

Data Index: 1613201 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6900. Min Act: -0.1700

Data Index: 4840946 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6682. Min Act: -0.1700

Data Index: 2851710 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6655. Min Act: -0.1700

Data Index: 7896374 (Open Web Text)

Max Activating Token Index: 783

Text #12

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6645. Min Act: -0.1700

Data Index: 4134641 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6771. Min Act: -0.1700

Data Index: 5182312 (Open Web Text)

Max Activating Token Index: 554

Text #14

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6501. Min Act: -0.1700

Data Index: 6558124 (Open Web Text)

Max Activating Token Index: 170

Text #15

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6476. Min Act: -0.1700

Data Index: 4199242 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6478. Min Act: -0.1700

Data Index: 7013837 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6726. Min Act: -0.1700

Data Index: 4720191 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6220. Min Act: -0.1700

Data Index: 1781879 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 4.9005. Min Range: -4.9005

Max Act: 4.6377. Min Act: -0.1700

Data Index: 7057519 (Open Web Text)

Max Activating Token Index: 653