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

Dataset: Open Web Text

Neuron 1683 in Layer 0

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: 3.8445. Min Range: -3.8445

Max Act: 3.8445. Min Act: -0.1700

Data Index: 8435242 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.8068. Min Act: -0.1700

Data Index: 5042174 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.8090. Min Act: -0.1700

Data Index: 3019442 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7712. Min Act: -0.1700

Data Index: 4711181 (Open Web Text)

Max Activating Token Index: 65

Text #4

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7904. Min Act: -0.1700

Data Index: 2352473 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7482. Min Act: -0.1700

Data Index: 8472797 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7105. Min Act: -0.1700

Data Index: 6530741 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7100. Min Act: -0.1700

Data Index: 8481941 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7222. Min Act: -0.1700

Data Index: 1569592 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7211. Min Act: -0.1700

Data Index: 2624504 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7084. Min Act: -0.1700

Data Index: 4362297 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6922. Min Act: -0.1700

Data Index: 5367340 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6799. Min Act: -0.1700

Data Index: 4060493 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6797. Min Act: -0.1700

Data Index: 6764340 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6889. Min Act: -0.1700

Data Index: 6791329 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.7051. Min Act: -0.1700

Data Index: 100695 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6886. Min Act: -0.1700

Data Index: 7388495 (Open Web Text)

Max Activating Token Index: 375

Text #17

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6743. Min Act: -0.1700

Data Index: 2448137 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6910. Min Act: -0.1700

Data Index: 5250768 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 3.8445. Min Range: -3.8445

Max Act: 3.6682. Min Act: -0.1700

Data Index: 2323224 (Open Web Text)

Max Activating Token Index: 875