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

Dataset: Open Web Text

Neuron 2487 in Layer 4

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: 3.0773. Min Range: -3.0773

Max Act: 3.0773. Min Act: -0.1700

Data Index: 2322755 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9621. Min Act: -0.1700

Data Index: 1260848 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9552. Min Act: -0.1700

Data Index: 3841753 (Open Web Text)

Max Activating Token Index: 733

Text #3

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9546. Min Act: -0.1700

Data Index: 5537063 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9596. Min Act: -0.1700

Data Index: 1312481 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9427. Min Act: -0.1700

Data Index: 3026823 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9302. Min Act: -0.1700

Data Index: 7790565 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9270. Min Act: -0.1700

Data Index: 2111569 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9057. Min Act: -0.1700

Data Index: 407919 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8911. Min Act: -0.1700

Data Index: 6344376 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.9098. Min Act: -0.1700

Data Index: 6683673 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8896. Min Act: -0.1700

Data Index: 2678028 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8915. Min Act: -0.1700

Data Index: 5150138 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8803. Min Act: -0.1700

Data Index: 3495210 (Open Web Text)

Max Activating Token Index: 858

Text #14

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8965. Min Act: -0.1700

Data Index: 5348569 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8971. Min Act: -0.1700

Data Index: 264922 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8459. Min Act: -0.1700

Data Index: 5608190 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8788. Min Act: -0.1700

Data Index: 4337307 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8825. Min Act: -0.1700

Data Index: 6295442 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 3.0773. Min Range: -3.0773

Max Act: 2.8822. Min Act: -0.1700

Data Index: 1043618 (Open Web Text)

Max Activating Token Index: 323