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

Dataset: Open Web Text

Neuron 2463 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: 4.6829. Min Range: -4.6829

Max Act: 4.6829. Min Act: -0.1700

Data Index: 8548836 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.6368. Min Act: -0.1700

Data Index: 8266152 (Open Web Text)

Max Activating Token Index: 60

Text #2

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.6406. Min Act: -0.1700

Data Index: 2608571 (Open Web Text)

Max Activating Token Index: 652

Text #3

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5813. Min Act: -0.1700

Data Index: 3715320 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5576. Min Act: -0.1700

Data Index: 6703876 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5373. Min Act: -0.1700

Data Index: 6024454 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4944. Min Act: -0.1700

Data Index: 234900 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5449. Min Act: -0.1700

Data Index: 3241626 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5272. Min Act: -0.1700

Data Index: 8579547 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5252. Min Act: -0.1700

Data Index: 5715927 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5023. Min Act: -0.1700

Data Index: 766544 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.5207. Min Act: -0.1700

Data Index: 6717106 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4816. Min Act: -0.1700

Data Index: 6335093 (Open Web Text)

Max Activating Token Index: 349

Text #13

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4979. Min Act: -0.1700

Data Index: 266961 (Open Web Text)

Max Activating Token Index: 125

Text #14

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4729. Min Act: -0.1700

Data Index: 6177322 (Open Web Text)

Max Activating Token Index: 877

Text #15

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4518. Min Act: -0.1700

Data Index: 3681140 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4577. Min Act: -0.1700

Data Index: 6398959 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4292. Min Act: -0.1700

Data Index: 8615745 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4318. Min Act: -0.1700

Data Index: 743790 (Open Web Text)

Max Activating Token Index: 644

Text #19

Max Range: 4.6829. Min Range: -4.6829

Max Act: 4.4567. Min Act: -0.1700

Data Index: 616944 (Open Web Text)

Max Activating Token Index: 21