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

Dataset: Open Web Text

Neuron 2903 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: 0.6889. Min Range: -0.6889

Max Act: 0.6889. Min Act: -0.0896

Data Index: 2623725 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6706. Min Act: -0.0935

Data Index: 8124497 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6616. Min Act: -0.0286

Data Index: 5915890 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6592. Min Act: -0.0764

Data Index: 5731768 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6575. Min Act: -0.0612

Data Index: 5349023 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6571. Min Act: -0.0745

Data Index: 6437146 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6550. Min Act: -0.0820

Data Index: 95262 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6567. Min Act: 0.0429

Data Index: 3130270 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6477. Min Act: 0.0525

Data Index: 2758338 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6465. Min Act: -0.0897

Data Index: 8124493 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6478. Min Act: -0.0110

Data Index: 1496378 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6457. Min Act: -0.0601

Data Index: 7464264 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6416. Min Act: 0.0525

Data Index: 7380024 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6465. Min Act: -0.0435

Data Index: 7442658 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6438. Min Act: -0.0883

Data Index: 6024120 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6432. Min Act: -0.0375

Data Index: 6339711 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6419. Min Act: -0.0091

Data Index: 6584761 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6411. Min Act: -0.0595

Data Index: 249890 (Open Web Text)

Max Activating Token Index: 660

Text #18

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6395. Min Act: -0.0976

Data Index: 3359991 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6406. Min Act: -0.0353

Data Index: 7686474 (Open Web Text)

Max Activating Token Index: 818