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

Dataset: Open Web Text

Neuron 268 in Layer 1

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: 3.5444. Min Range: -3.5444

Max Act: 3.5444. Min Act: -0.1700

Data Index: 3985047 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.4605. Min Act: -0.1700

Data Index: 6315626 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3863. Min Act: -0.1700

Data Index: 678794 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.4283. Min Act: -0.1700

Data Index: 4536500 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3917. Min Act: -0.1700

Data Index: 5978585 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3351. Min Act: -0.1700

Data Index: 5036247 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2931. Min Act: -0.1700

Data Index: 1708441 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3085. Min Act: -0.1700

Data Index: 5881876 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3189. Min Act: -0.1700

Data Index: 3588618 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2818. Min Act: -0.1700

Data Index: 7101704 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2670. Min Act: -0.1700

Data Index: 6050933 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2749. Min Act: -0.1700

Data Index: 7229441 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2566. Min Act: -0.1700

Data Index: 5209025 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2187. Min Act: -0.1700

Data Index: 5873468 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2439. Min Act: -0.1700

Data Index: 6946658 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.1867. Min Act: -0.1700

Data Index: 6206991 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2169. Min Act: -0.1700

Data Index: 5485038 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.1913. Min Act: -0.1700

Data Index: 6527073 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2038. Min Act: -0.1700

Data Index: 4736544 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.1948. Min Act: -0.1700

Data Index: 3939472 (Open Web Text)

Max Activating Token Index: 1023