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

Dataset: Open Web Text

Neuron 1927 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: 3.6701. Min Range: -3.6701

Max Act: 3.6305. Min Act: -0.1700

Data Index: 493142 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6282. Min Act: -0.1700

Data Index: 212795 (Open Web Text)

Max Activating Token Index: 902

Text #2

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6701. Min Act: -0.1700

Data Index: 8433079 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6512. Min Act: -0.1700

Data Index: 3664385 (Open Web Text)

Max Activating Token Index: 907

Text #4

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6242. Min Act: -0.1700

Data Index: 8600116 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6254. Min Act: -0.1700

Data Index: 8052771 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6152. Min Act: -0.1700

Data Index: 7837755 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5672. Min Act: -0.1700

Data Index: 6649835 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5817. Min Act: -0.1700

Data Index: 1731758 (Open Web Text)

Max Activating Token Index: 827

Text #9

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5772. Min Act: -0.1700

Data Index: 1150630 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5809. Min Act: -0.1700

Data Index: 530650 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5909. Min Act: -0.1700

Data Index: 6958295 (Open Web Text)

Max Activating Token Index: 972

Text #12

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5930. Min Act: -0.1700

Data Index: 1950460 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5759. Min Act: -0.1700

Data Index: 5895614 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5666. Min Act: -0.1700

Data Index: 5852803 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5771. Min Act: -0.1700

Data Index: 3870697 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5880. Min Act: -0.1700

Data Index: 3769537 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5892. Min Act: -0.1700

Data Index: 1665336 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.6003. Min Act: -0.1700

Data Index: 1468290 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 3.6701. Min Range: -3.6701

Max Act: 3.5559. Min Act: -0.1700

Data Index: 5660816 (Open Web Text)

Max Activating Token Index: 194