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

Dataset: Open Web Text

Neuron 2440 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: 3.8816. Min Range: -3.8816

Max Act: 3.8816. Min Act: -0.1700

Data Index: 2688193 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7942. Min Act: -0.1700

Data Index: 4015466 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7750. Min Act: -0.1700

Data Index: 654951 (Open Web Text)

Max Activating Token Index: 871

Text #3

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.8048. Min Act: -0.1700

Data Index: 5741794 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7042. Min Act: -0.1700

Data Index: 1209131 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7146. Min Act: -0.1700

Data Index: 3568120 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7251. Min Act: -0.1700

Data Index: 7783003 (Open Web Text)

Max Activating Token Index: 702

Text #7

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7108. Min Act: -0.1700

Data Index: 6850031 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7338. Min Act: -0.1700

Data Index: 6510948 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7059. Min Act: -0.1700

Data Index: 4629431 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6805. Min Act: -0.1700

Data Index: 2075730 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6621. Min Act: -0.1700

Data Index: 2513507 (Open Web Text)

Max Activating Token Index: 937

Text #12

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6773. Min Act: -0.1700

Data Index: 4095764 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6736. Min Act: -0.1700

Data Index: 7792586 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.7027. Min Act: -0.1700

Data Index: 1032887 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6359. Min Act: -0.1700

Data Index: 3737116 (Open Web Text)

Max Activating Token Index: 919

Text #16

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6674. Min Act: -0.1700

Data Index: 4917538 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6594. Min Act: -0.1700

Data Index: 4393661 (Open Web Text)

Max Activating Token Index: 80

Text #18

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6822. Min Act: -0.1700

Data Index: 5918472 (Open Web Text)

Max Activating Token Index: 704

Text #19

Max Range: 3.8816. Min Range: -3.8816

Max Act: 3.6393. Min Act: -0.1700

Data Index: 6395874 (Open Web Text)

Max Activating Token Index: 437