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

Dataset: Open Web Text

Neuron 3001 in Layer 3

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: 4.1614. Min Range: -4.1614

Max Act: 4.1614. Min Act: -0.1700

Data Index: 6001397 (Open Web Text)

Max Activating Token Index: 231

Text #1

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.8914. Min Act: -0.1700

Data Index: 5781908 (Open Web Text)

Max Activating Token Index: 853

Text #2

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.9031. Min Act: -0.1700

Data Index: 4720157 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.8828. Min Act: -0.1700

Data Index: 8129933 (Open Web Text)

Max Activating Token Index: 964

Text #4

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7958. Min Act: -0.1699

Data Index: 6974361 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.8294. Min Act: -0.1700

Data Index: 6024985 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.8051. Min Act: -0.1700

Data Index: 5820074 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7715. Min Act: -0.1700

Data Index: 7489661 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7628. Min Act: -0.1700

Data Index: 4950467 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7977. Min Act: -0.1700

Data Index: 5478435 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7614. Min Act: -0.1700

Data Index: 8511292 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7242. Min Act: -0.1700

Data Index: 521039 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7361. Min Act: -0.1700

Data Index: 6576337 (Open Web Text)

Max Activating Token Index: 111

Text #13

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.6885. Min Act: -0.1700

Data Index: 6041869 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7109. Min Act: -0.1700

Data Index: 6592472 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7350. Min Act: -0.1700

Data Index: 7224456 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7132. Min Act: -0.1700

Data Index: 8292714 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.6823. Min Act: -0.1700

Data Index: 6350461 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.7068. Min Act: -0.1700

Data Index: 1069798 (Open Web Text)

Max Activating Token Index: 704

Text #19

Max Range: 4.1614. Min Range: -4.1614

Max Act: 3.6924. Min Act: -0.1700

Data Index: 8221305 (Open Web Text)

Max Activating Token Index: 279