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

Dataset: Open Web Text

Neuron 105 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: 3.2677. Min Range: -3.2677

Max Act: 3.2677. Min Act: -0.1700

Data Index: 1702012 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.1309. Min Act: -0.1700

Data Index: 3394623 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.0132. Min Act: -0.1700

Data Index: 8096861 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9948. Min Act: -0.1700

Data Index: 3085452 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9571. Min Act: -0.1700

Data Index: 4978541 (Open Web Text)

Max Activating Token Index: 935

Text #5

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9644. Min Act: -0.1700

Data Index: 8267920 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8872. Min Act: -0.1700

Data Index: 5699891 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9539. Min Act: -0.1700

Data Index: 6613032 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9127. Min Act: -0.1700

Data Index: 2041993 (Open Web Text)

Max Activating Token Index: 935

Text #9

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8730. Min Act: -0.1700

Data Index: 3719636 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8586. Min Act: -0.1700

Data Index: 8584036 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.9061. Min Act: -0.1700

Data Index: 8288099 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8724. Min Act: -0.1700

Data Index: 2035682 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8366. Min Act: -0.1700

Data Index: 3924647 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8556. Min Act: -0.1700

Data Index: 8268236 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8440. Min Act: -0.1700

Data Index: 6605829 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8358. Min Act: -0.1700

Data Index: 2149592 (Open Web Text)

Max Activating Token Index: 896

Text #17

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8270. Min Act: -0.1700

Data Index: 7568633 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8270. Min Act: -0.1700

Data Index: 7118752 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.8335. Min Act: -0.1700

Data Index: 4791392 (Open Web Text)

Max Activating Token Index: 931