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

Dataset: Open Web Text

Neuron 509 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: 4.8436. Min Range: -4.8436

Max Act: 4.8436. Min Act: -0.1699

Data Index: 6094077 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.4646. Min Act: -0.1700

Data Index: 6778330 (Open Web Text)

Max Activating Token Index: 96

Text #2

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.4409. Min Act: -0.1700

Data Index: 123815 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.2699. Min Act: -0.1700

Data Index: 7676658 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.2880. Min Act: -0.1700

Data Index: 5973578 (Open Web Text)

Max Activating Token Index: 176

Text #5

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.2513. Min Act: -0.1700

Data Index: 7422329 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1931. Min Act: -0.1700

Data Index: 5250380 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1808. Min Act: -0.1700

Data Index: 965026 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1720. Min Act: -0.1700

Data Index: 7013502 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1984. Min Act: -0.1700

Data Index: 3007514 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1784. Min Act: -0.1700

Data Index: 6094076 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1335. Min Act: -0.1700

Data Index: 215694 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1322. Min Act: -0.1693

Data Index: 1167179 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0423. Min Act: -0.1700

Data Index: 1037205 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0582. Min Act: -0.1700

Data Index: 5396425 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0638. Min Act: -0.1700

Data Index: 6287343 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0379. Min Act: -0.1700

Data Index: 2262147 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0272. Min Act: -0.1700

Data Index: 5438754 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0400. Min Act: -0.1700

Data Index: 2888423 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.9808. Min Act: -0.1700

Data Index: 5250379 (Open Web Text)

Max Activating Token Index: 523