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

Dataset: Open Web Text

Neuron 1981 in Layer 6

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: 3.3686. Min Range: -3.3686

Max Act: 3.3686. Min Act: -0.1700

Data Index: 3197504 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.3533. Min Act: -0.1700

Data Index: 7141302 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.3204. Min Act: -0.1700

Data Index: 3923388 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2942. Min Act: -0.1700

Data Index: 6410523 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2993. Min Act: -0.1700

Data Index: 3412123 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2625. Min Act: -0.1700

Data Index: 7218387 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2793. Min Act: -0.1700

Data Index: 3017160 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2636. Min Act: -0.1700

Data Index: 1241119 (Open Web Text)

Max Activating Token Index: 1004

Text #8

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.2159. Min Act: -0.1700

Data Index: 4050872 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1747. Min Act: -0.1700

Data Index: 1460840 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1843. Min Act: -0.1700

Data Index: 7475021 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1857. Min Act: -0.1700

Data Index: 3245900 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1503. Min Act: -0.1700

Data Index: 5150051 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1122122 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1756. Min Act: -0.1700

Data Index: 494931 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1404. Min Act: -0.1700

Data Index: 3752876 (Open Web Text)

Max Activating Token Index: 1004

Text #16

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1550. Min Act: -0.1700

Data Index: 6831724 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1289. Min Act: -0.1700

Data Index: 4133749 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1424. Min Act: -0.1700

Data Index: 2928040 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 3.3686. Min Range: -3.3686

Max Act: 3.1334. Min Act: -0.1700

Data Index: 6730294 (Open Web Text)

Max Activating Token Index: 766