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

Dataset: Open Web Text

Neuron 1550 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: 3.5508. Min Range: -3.5508

Max Act: 3.5508. Min Act: -0.1700

Data Index: 8296574 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3828. Min Act: -0.1700

Data Index: 2454168 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2521. Min Act: -0.1700

Data Index: 842676 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2705. Min Act: -0.1700

Data Index: 2220119 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2698. Min Act: -0.1700

Data Index: 8500465 (Open Web Text)

Max Activating Token Index: 619

Text #5

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2266. Min Act: -0.1700

Data Index: 589429 (Open Web Text)

Max Activating Token Index: 683

Text #6

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2113. Min Act: -0.1700

Data Index: 6963646 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2098. Min Act: -0.1700

Data Index: 1279517 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1901. Min Act: -0.1700

Data Index: 2581482 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1743. Min Act: -0.1700

Data Index: 6995803 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2134. Min Act: -0.1700

Data Index: 7878265 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1832. Min Act: -0.1700

Data Index: 6462151 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1828. Min Act: -0.1700

Data Index: 5832184 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2041. Min Act: -0.1700

Data Index: 2460238 (Open Web Text)

Max Activating Token Index: 635

Text #14

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1696. Min Act: -0.1700

Data Index: 4946516 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1678. Min Act: -0.1700

Data Index: 8148554 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1625. Min Act: -0.1700

Data Index: 5283111 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1776. Min Act: -0.1700

Data Index: 4161131 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1712. Min Act: -0.1700

Data Index: 2262616 (Open Web Text)

Max Activating Token Index: 899

Text #19

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.1653. Min Act: -0.1700

Data Index: 1918635 (Open Web Text)

Max Activating Token Index: 165