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

Dataset: Open Web Text

Neuron 801 in Layer 5

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: 4.9917. Min Range: -4.9917

Max Act: 4.9917. Min Act: -0.1700

Data Index: 4175304 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.9903. Min Act: -0.1700

Data Index: 7477093 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.9275. Min Act: -0.1700

Data Index: 5237225 (Open Web Text)

Max Activating Token Index: 873

Text #3

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.9065. Min Act: -0.1700

Data Index: 697337 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.9419. Min Act: -0.1700

Data Index: 1947471 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8843. Min Act: -0.1700

Data Index: 6768987 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8824. Min Act: -0.1700

Data Index: 5674485 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8711. Min Act: -0.1700

Data Index: 7563649 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8449. Min Act: -0.1700

Data Index: 7312668 (Open Web Text)

Max Activating Token Index: 423

Text #9

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8506. Min Act: -0.1700

Data Index: 3018878 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8850. Min Act: -0.1700

Data Index: 8002696 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8724. Min Act: -0.1700

Data Index: 7608172 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8679. Min Act: -0.1700

Data Index: 7020568 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8394. Min Act: -0.1700

Data Index: 4994289 (Open Web Text)

Max Activating Token Index: 849

Text #14

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8204. Min Act: -0.1700

Data Index: 603773 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8271. Min Act: -0.1700

Data Index: 1601405 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7959. Min Act: -0.1700

Data Index: 3514191 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7943. Min Act: -0.1700

Data Index: 4073127 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7950. Min Act: -0.1700

Data Index: 2051461 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7821. Min Act: -0.1700

Data Index: 1138641 (Open Web Text)

Max Activating Token Index: 658