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

Dataset: Open Web Text

Neuron 703 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: 3.3332. Min Range: -3.3332

Max Act: 3.3332. Min Act: -0.1700

Data Index: 8666032 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.2306. Min Act: -0.1700

Data Index: 6012377 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1885. Min Act: -0.1700

Data Index: 4212913 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1532. Min Act: -0.1700

Data Index: 6797619 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1669. Min Act: -0.1700

Data Index: 3414262 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1552. Min Act: -0.1700

Data Index: 5206521 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1228. Min Act: -0.1700

Data Index: 7860178 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1043. Min Act: -0.1700

Data Index: 7692801 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.1093. Min Act: -0.1700

Data Index: 1440164 (Open Web Text)

Max Activating Token Index: 710

Text #9

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0738. Min Act: -0.1700

Data Index: 525597 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0746. Min Act: -0.1700

Data Index: 2084238 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0862. Min Act: -0.1700

Data Index: 4211076 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0623. Min Act: -0.1700

Data Index: 2982202 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0408. Min Act: -0.1700

Data Index: 1981298 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0467. Min Act: -0.1700

Data Index: 6961231 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0424. Min Act: -0.1700

Data Index: 7199541 (Open Web Text)

Max Activating Token Index: 124

Text #16

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0283. Min Act: -0.1700

Data Index: 2015708 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 3.3332. Min Range: -3.3332

Max Act: 2.9910. Min Act: -0.1700

Data Index: 4210357 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.3332. Min Range: -3.3332

Max Act: 3.0175. Min Act: -0.1700

Data Index: 2645166 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 3.3332. Min Range: -3.3332

Max Act: 2.9919. Min Act: -0.1700

Data Index: 6991952 (Open Web Text)

Max Activating Token Index: 778