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

Dataset: Open Web Text

Neuron 2916 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: 3.5081. Min Range: -3.5081

Max Act: 3.5081. Min Act: -0.1700

Data Index: 6258508 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4307. Min Act: -0.1700

Data Index: 5384971 (Open Web Text)

Max Activating Token Index: 321

Text #2

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4421. Min Act: -0.1700

Data Index: 8456302 (Open Web Text)

Max Activating Token Index: 958

Text #3

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4183. Min Act: -0.1700

Data Index: 6229932 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4142. Min Act: -0.1700

Data Index: 8523756 (Open Web Text)

Max Activating Token Index: 792

Text #5

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4381. Min Act: -0.1700

Data Index: 6696023 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.4227. Min Act: -0.1700

Data Index: 7735790 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3946. Min Act: -0.1700

Data Index: 5215855 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3881. Min Act: -0.1700

Data Index: 6258496 (Open Web Text)

Max Activating Token Index: 853

Text #9

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3775. Min Act: -0.1700

Data Index: 6258505 (Open Web Text)

Max Activating Token Index: 796

Text #10

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3827. Min Act: -0.1700

Data Index: 8697522 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3697. Min Act: -0.1700

Data Index: 8173515 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3663. Min Act: -0.1700

Data Index: 13434 (Open Web Text)

Max Activating Token Index: 801

Text #13

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3697. Min Act: -0.1700

Data Index: 3686241 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3740. Min Act: -0.1700

Data Index: 5266762 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3523. Min Act: -0.1700

Data Index: 6644344 (Open Web Text)

Max Activating Token Index: 525

Text #16

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3606. Min Act: -0.1700

Data Index: 3171115 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3324. Min Act: -0.1700

Data Index: 2166725 (Open Web Text)

Max Activating Token Index: 490

Text #18

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3399. Min Act: -0.1700

Data Index: 6258498 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 3.5081. Min Range: -3.5081

Max Act: 3.3459. Min Act: -0.1700

Data Index: 403809 (Open Web Text)

Max Activating Token Index: 471