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

Dataset: Open Web Text

Neuron 2239 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: 1.6801. Min Range: -1.6801

Max Act: 1.6801. Min Act: -0.1700

Data Index: 601904 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6730. Min Act: -0.1694

Data Index: 5349075 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6468. Min Act: -0.1700

Data Index: 2464966 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6292. Min Act: -0.1700

Data Index: 1929681 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6403. Min Act: -0.1700

Data Index: 4124066 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6328. Min Act: -0.1691

Data Index: 1368380 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6383. Min Act: -0.1700

Data Index: 4975759 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6303. Min Act: -0.1700

Data Index: 1182014 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6217. Min Act: -0.1700

Data Index: 5231205 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6215. Min Act: -0.1700

Data Index: 5309318 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6353. Min Act: -0.1699

Data Index: 3347653 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6307. Min Act: -0.1700

Data Index: 2881719 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6375. Min Act: -0.1700

Data Index: 1467975 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6292. Min Act: -0.1700

Data Index: 602676 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6022. Min Act: -0.1700

Data Index: 2291290 (Open Web Text)

Max Activating Token Index: 509

Text #15

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6108. Min Act: -0.1700

Data Index: 5417850 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6147. Min Act: -0.1700

Data Index: 3885590 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6089. Min Act: -0.1700

Data Index: 5936039 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6090. Min Act: -0.1700

Data Index: 6533520 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6093. Min Act: -0.1700

Data Index: 1547004 (Open Web Text)

Max Activating Token Index: 198