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

Dataset: Open Web Text

Neuron 394 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: 3.2885. Min Range: -3.2885

Max Act: 3.2885. Min Act: -0.1700

Data Index: 4109659 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1806. Min Act: -0.1700

Data Index: 5764050 (Open Web Text)

Max Activating Token Index: 202

Text #2

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1654. Min Act: -0.1700

Data Index: 2744417 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1415. Min Act: -0.1700

Data Index: 376649 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1521. Min Act: -0.1700

Data Index: 6265744 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1259. Min Act: -0.1700

Data Index: 893993 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1320. Min Act: -0.1700

Data Index: 2713944 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1270. Min Act: -0.1700

Data Index: 895726 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1092. Min Act: -0.1700

Data Index: 4927411 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1171. Min Act: -0.1700

Data Index: 2138490 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1002. Min Act: -0.1700

Data Index: 930797 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0936. Min Act: -0.1700

Data Index: 3243405 (Open Web Text)

Max Activating Token Index: 796

Text #12

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0824. Min Act: -0.1700

Data Index: 2852671 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0827. Min Act: -0.1700

Data Index: 6294563 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1011. Min Act: -0.1700

Data Index: 5998744 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0810. Min Act: -0.1700

Data Index: 7263601 (Open Web Text)

Max Activating Token Index: 992

Text #16

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0761. Min Act: -0.1700

Data Index: 2601057 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0594. Min Act: -0.1700

Data Index: 2559465 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0698. Min Act: -0.1700

Data Index: 1028495 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0396. Min Act: -0.1700

Data Index: 3818117 (Open Web Text)

Max Activating Token Index: 739