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

Dataset: Open Web Text

Neuron 2661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.8757. Min Act: -0.1700

Data Index: 2424796 (Open Web Text)

Max Activating Token Index: 364

Text #1

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7542. Min Act: -0.1700

Data Index: 3001299 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7544. Min Act: -0.1700

Data Index: 1539133 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7818. Min Act: -0.1700

Data Index: 3586871 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7218. Min Act: -0.1700

Data Index: 4685623 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7271. Min Act: -0.1700

Data Index: 7869540 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7171. Min Act: -0.1700

Data Index: 8511326 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.7369. Min Act: -0.1700

Data Index: 6225008 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6980. Min Act: -0.1700

Data Index: 475008 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6867. Min Act: -0.1700

Data Index: 5040927 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6829. Min Act: -0.1700

Data Index: 874017 (Open Web Text)

Max Activating Token Index: 759

Text #11

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6554. Min Act: -0.1700

Data Index: 8546999 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6710. Min Act: -0.1700

Data Index: 6489860 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6617. Min Act: -0.1700

Data Index: 3074827 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6555. Min Act: -0.1700

Data Index: 7161639 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6324. Min Act: -0.1700

Data Index: 3602813 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6327. Min Act: -0.1700

Data Index: 7186260 (Open Web Text)

Max Activating Token Index: 903

Text #17

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6604. Min Act: -0.1700

Data Index: 1965234 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.6667. Min Act: -0.1700

Data Index: 1313656 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 5.8757. Min Range: -5.8757

Max Act: 5.5932. Min Act: -0.1700

Data Index: 71072 (Open Web Text)

Max Activating Token Index: 417