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

Dataset: Open Web Text

Neuron 533 in Layer 4

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: 2.9545. Min Range: -2.9545

Max Act: 2.9545. Min Act: -0.1700

Data Index: 2545164 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8863. Min Act: -0.1700

Data Index: 11799 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8520. Min Act: -0.1700

Data Index: 3347594 (Open Web Text)

Max Activating Token Index: 820

Text #3

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8300. Min Act: -0.1700

Data Index: 2186768 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8498. Min Act: -0.1700

Data Index: 7951067 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8422. Min Act: -0.1700

Data Index: 3440607 (Open Web Text)

Max Activating Token Index: 876

Text #6

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8391. Min Act: -0.1700

Data Index: 8062908 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8224. Min Act: -0.1700

Data Index: 544495 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7788. Min Act: -0.1700

Data Index: 4372573 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7896. Min Act: -0.1700

Data Index: 8114882 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7657. Min Act: -0.1700

Data Index: 2807525 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7542. Min Act: -0.1700

Data Index: 4166956 (Open Web Text)

Max Activating Token Index: 759

Text #12

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7670. Min Act: -0.1700

Data Index: 4952727 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7500. Min Act: -0.1700

Data Index: 2553263 (Open Web Text)

Max Activating Token Index: 506

Text #14

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7392. Min Act: -0.1700

Data Index: 5957577 (Open Web Text)

Max Activating Token Index: 886

Text #15

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7201. Min Act: -0.1700

Data Index: 2540997 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7278. Min Act: -0.1700

Data Index: 3327964 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7147. Min Act: -0.1700

Data Index: 8395635 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7273. Min Act: -0.1700

Data Index: 885289 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7202. Min Act: -0.1700

Data Index: 3334384 (Open Web Text)

Max Activating Token Index: 772