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

Dataset: Open Web Text

Neuron 2900 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: 2.2890. Min Range: -2.2890

Max Act: 2.2890. Min Act: -0.1700

Data Index: 7192852 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.1699. Min Act: -0.1700

Data Index: 8491711 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.1403. Min Act: -0.1700

Data Index: 2580782 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.1337. Min Act: -0.1700

Data Index: 4744683 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0985. Min Act: -0.1700

Data Index: 8354141 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0935. Min Act: -0.1700

Data Index: 2103132 (Open Web Text)

Max Activating Token Index: 103

Text #6

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0586. Min Act: -0.1700

Data Index: 6255472 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0156. Min Act: -0.1700

Data Index: 4275743 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0619. Min Act: -0.1700

Data Index: 8452270 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0257. Min Act: -0.1700

Data Index: 2301378 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0196. Min Act: -0.1700

Data Index: 7775705 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0170. Min Act: -0.1700

Data Index: 834448 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9949. Min Act: -0.1700

Data Index: 5091753 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9877. Min Act: -0.1700

Data Index: 277596 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9705. Min Act: -0.1700

Data Index: 6742167 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9858. Min Act: -0.1700

Data Index: 6164550 (Open Web Text)

Max Activating Token Index: 149

Text #16

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9826. Min Act: -0.1700

Data Index: 375065 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9755. Min Act: -0.1700

Data Index: 8055218 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9672. Min Act: -0.1700

Data Index: 1106480 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9713. Min Act: -0.1700

Data Index: 35246 (Open Web Text)

Max Activating Token Index: 33