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

Dataset: Open Web Text

Neuron 1953 in Layer 2

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: 4.1494. Min Range: -4.1494

Max Act: 4.1494. Min Act: -0.1684

Data Index: 4479115 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 4.1494. Min Range: -4.1494

Max Act: 4.1051. Min Act: -0.1697

Data Index: 2787134 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 4.1494. Min Range: -4.1494

Max Act: 4.0951. Min Act: -0.1696

Data Index: 1477645 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 4.1494. Min Range: -4.1494

Max Act: 4.0570. Min Act: -0.1670

Data Index: 7490619 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.9178. Min Act: -0.1295

Data Index: 2787137 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8928. Min Act: -0.1699

Data Index: 6140839 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.9042. Min Act: -0.1699

Data Index: 1477632 (Open Web Text)

Max Activating Token Index: 158

Text #7

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8741. Min Act: -0.1224

Data Index: 1477616 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8809. Min Act: -0.1700

Data Index: 1477623 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8650. Min Act: -0.1700

Data Index: 4479113 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8312. Min Act: -0.1274

Data Index: 6140843 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8340. Min Act: -0.1700

Data Index: 6140844 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8671. Min Act: -0.1670

Data Index: 2787136 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8061. Min Act: -0.1700

Data Index: 4479111 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8234. Min Act: -0.1700

Data Index: 6140834 (Open Web Text)

Max Activating Token Index: 236

Text #15

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8072. Min Act: -0.1700

Data Index: 1474825 (Open Web Text)

Max Activating Token Index: 85

Text #16

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7744. Min Act: -0.1700

Data Index: 2787133 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7722. Min Act: -0.1665

Data Index: 6140842 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7790. Min Act: -0.1700

Data Index: 1477608 (Open Web Text)

Max Activating Token Index: 118

Text #19

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7831. Min Act: -0.1304

Data Index: 1477642 (Open Web Text)

Max Activating Token Index: 690