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

Dataset: Open Web Text

Neuron 2153 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: 4.2509. Min Range: -4.2509

Max Act: 4.2509. Min Act: -0.1700

Data Index: 5065174 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 4.2509. Min Range: -4.2509

Max Act: 4.1040. Min Act: -0.1700

Data Index: 5433291 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.2509. Min Range: -4.2509

Max Act: 4.0153. Min Act: -0.1700

Data Index: 4590963 (Open Web Text)

Max Activating Token Index: 790

Text #3

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.9689. Min Act: -0.1700

Data Index: 2430921 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.9911. Min Act: -0.1700

Data Index: 947444 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.9097. Min Act: -0.1700

Data Index: 7929293 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8619. Min Act: -0.1700

Data Index: 5589163 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8898. Min Act: -0.1700

Data Index: 3557521 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8932. Min Act: -0.1700

Data Index: 601248 (Open Web Text)

Max Activating Token Index: 131

Text #9

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8425. Min Act: -0.1700

Data Index: 2274827 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8486. Min Act: -0.1700

Data Index: 1649587 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8067. Min Act: -0.1700

Data Index: 3105010 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8201. Min Act: -0.1700

Data Index: 8467877 (Open Web Text)

Max Activating Token Index: 56

Text #13

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8129. Min Act: -0.1700

Data Index: 4956034 (Open Web Text)

Max Activating Token Index: 185

Text #14

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.7947. Min Act: -0.1700

Data Index: 6556481 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.7957. Min Act: -0.1700

Data Index: 740133 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.8035. Min Act: -0.1700

Data Index: 1046483 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.7458. Min Act: -0.1700

Data Index: 6983789 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.7459. Min Act: -0.1700

Data Index: 6086606 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 4.2509. Min Range: -4.2509

Max Act: 3.7636. Min Act: -0.1700

Data Index: 7402141 (Open Web Text)

Max Activating Token Index: 575