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

Dataset: Open Web Text

Neuron 1450 in Layer 3

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: 5.2549. Min Range: -5.2549

Max Act: 5.2549. Min Act: -0.1700

Data Index: 4406519 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.1417. Min Act: -0.1700

Data Index: 4416842 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.0368. Min Act: -0.1700

Data Index: 2110158 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.0574. Min Act: -0.1700

Data Index: 6493085 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.0082. Min Act: -0.1700

Data Index: 8011929 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.0060. Min Act: -0.1700

Data Index: 670716 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9947. Min Act: -0.1700

Data Index: 2995113 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 5.2549. Min Range: -5.2549

Max Act: 5.0006. Min Act: -0.1700

Data Index: 6881259 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9128. Min Act: -0.1700

Data Index: 4339850 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9983. Min Act: -0.1700

Data Index: 3832715 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9638. Min Act: -0.1700

Data Index: 1036691 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9126. Min Act: -0.1700

Data Index: 4697567 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9431. Min Act: -0.1700

Data Index: 6306555 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.9484. Min Act: -0.1700

Data Index: 4788318 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8785. Min Act: -0.1700

Data Index: 6160482 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8989. Min Act: -0.1700

Data Index: 3795214 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8905. Min Act: -0.1700

Data Index: 3202324 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8804. Min Act: -0.1700

Data Index: 7119019 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8755. Min Act: -0.1700

Data Index: 7942892 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 5.2549. Min Range: -5.2549

Max Act: 4.8850. Min Act: -0.1700

Data Index: 2614629 (Open Web Text)

Max Activating Token Index: 1023