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

Dataset: Open Web Text

Neuron 1612 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: 0.8658. Min Range: -0.8658

Max Act: 0.8658. Min Act: -0.1583

Data Index: 1511929 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.8476. Min Act: -0.1700

Data Index: 5274389 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.8078. Min Act: -0.1689

Data Index: 8222107 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.8083. Min Act: -0.1674

Data Index: 4211519 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7798. Min Act: -0.1698

Data Index: 457621 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7974. Min Act: -0.1700

Data Index: 7407799 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7891. Min Act: -0.1672

Data Index: 951800 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7958. Min Act: -0.1699

Data Index: 620645 (Open Web Text)

Max Activating Token Index: 871

Text #8

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7836. Min Act: -0.1700

Data Index: 555437 (Open Web Text)

Max Activating Token Index: 262

Text #9

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7926. Min Act: -0.1689

Data Index: 2705986 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7741. Min Act: -0.1657

Data Index: 2111980 (Open Web Text)

Max Activating Token Index: 493

Text #11

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7814. Min Act: -0.1700

Data Index: 5082571 (Open Web Text)

Max Activating Token Index: 248

Text #12

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7803. Min Act: -0.1699

Data Index: 92127 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7716. Min Act: -0.1699

Data Index: 3795726 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7726. Min Act: -0.1657

Data Index: 5252751 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7825. Min Act: -0.1690

Data Index: 1084127 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7752. Min Act: -0.1699

Data Index: 554398 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7650. Min Act: -0.1700

Data Index: 282740 (Open Web Text)

Max Activating Token Index: 996

Text #18

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7632. Min Act: -0.1700

Data Index: 5283322 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7711. Min Act: -0.1691

Data Index: 5564469 (Open Web Text)

Max Activating Token Index: 128