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

Dataset: Open Web Text

Neuron 1704 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: 1.9762. Min Range: -1.9762

Max Act: 1.9762. Min Act: -0.1700

Data Index: 4606339 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9621. Min Act: -0.1700

Data Index: 2782236 (Open Web Text)

Max Activating Token Index: 800

Text #2

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9622. Min Act: -0.1700

Data Index: 5338645 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9478. Min Act: -0.1700

Data Index: 2334368 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9500. Min Act: -0.1700

Data Index: 6147651 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9413. Min Act: -0.1700

Data Index: 4161063 (Open Web Text)

Max Activating Token Index: 846

Text #6

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9169. Min Act: -0.1700

Data Index: 5780221 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9155. Min Act: -0.1700

Data Index: 6636275 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9227. Min Act: -0.1700

Data Index: 3477000 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9150. Min Act: -0.1700

Data Index: 5693667 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9211. Min Act: -0.1699

Data Index: 1719816 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9138. Min Act: -0.1700

Data Index: 7232960 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9187. Min Act: -0.1700

Data Index: 1923624 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9073. Min Act: -0.1700

Data Index: 6627597 (Open Web Text)

Max Activating Token Index: 905

Text #14

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8899. Min Act: -0.1700

Data Index: 1873936 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8998. Min Act: -0.1700

Data Index: 4351652 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9035. Min Act: -0.1700

Data Index: 6518808 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8836. Min Act: -0.1700

Data Index: 3253539 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8986. Min Act: -0.1700

Data Index: 3847210 (Open Web Text)

Max Activating Token Index: 157

Text #19

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8859. Min Act: -0.1700

Data Index: 6508559 (Open Web Text)

Max Activating Token Index: 886