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

Dataset: Open Web Text

Neuron 1423 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: 1.9364. Min Range: -1.9364

Max Act: 1.9364. Min Act: -0.1699

Data Index: 2690141 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.9218. Min Act: -0.1700

Data Index: 5270985 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.9018. Min Act: -0.1700

Data Index: 2627781 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.9127. Min Act: -0.1698

Data Index: 1708906 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8901. Min Act: -0.1700

Data Index: 7029631 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8910. Min Act: -0.1700

Data Index: 7619264 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8913. Min Act: -0.1700

Data Index: 1377075 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8846. Min Act: -0.1699

Data Index: 86161 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8902. Min Act: -0.1700

Data Index: 2816051 (Open Web Text)

Max Activating Token Index: 167

Text #9

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8742. Min Act: -0.1700

Data Index: 1025993 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8838. Min Act: -0.1700

Data Index: 7360005 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8689. Min Act: -0.1700

Data Index: 6426440 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8846. Min Act: -0.1700

Data Index: 573717 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8594. Min Act: -0.1700

Data Index: 7302664 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8583. Min Act: -0.1700

Data Index: 7215871 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8627. Min Act: -0.1700

Data Index: 4677243 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8595. Min Act: -0.1700

Data Index: 6332984 (Open Web Text)

Max Activating Token Index: 746

Text #17

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8496. Min Act: -0.1700

Data Index: 3934845 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8622. Min Act: -0.1700

Data Index: 3655626 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8473. Min Act: -0.1700

Data Index: 3162558 (Open Web Text)

Max Activating Token Index: 187