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

Dataset: Open Web Text

Neuron 2731 in Layer 2

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: 2.3216. Min Range: -2.3216

Max Act: 2.3216. Min Act: -0.1700

Data Index: 419517 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.2719. Min Act: -0.1700

Data Index: 2774136 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1962. Min Act: -0.1700

Data Index: 4010349 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1925. Min Act: -0.1700

Data Index: 1399032 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1860. Min Act: -0.1700

Data Index: 3644679 (Open Web Text)

Max Activating Token Index: 1002

Text #5

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1482. Min Act: -0.1700

Data Index: 2408557 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1700. Min Act: -0.1700

Data Index: 2388698 (Open Web Text)

Max Activating Token Index: 929

Text #7

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1182. Min Act: -0.1700

Data Index: 7925325 (Open Web Text)

Max Activating Token Index: 995

Text #8

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1089. Min Act: -0.1700

Data Index: 4949908 (Open Web Text)

Max Activating Token Index: 611

Text #9

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0786. Min Act: -0.1700

Data Index: 2428515 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0956. Min Act: -0.1700

Data Index: 2820074 (Open Web Text)

Max Activating Token Index: 1008

Text #11

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1068. Min Act: -0.1700

Data Index: 517642 (Open Web Text)

Max Activating Token Index: 742

Text #12

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0684. Min Act: -0.1700

Data Index: 2315135 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1104. Min Act: -0.1700

Data Index: 4290649 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0724. Min Act: -0.1700

Data Index: 3002988 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0698. Min Act: -0.1700

Data Index: 1252826 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0373. Min Act: -0.1700

Data Index: 389794 (Open Web Text)

Max Activating Token Index: 890

Text #17

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0172. Min Act: -0.1700

Data Index: 3033287 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0513. Min Act: -0.1700

Data Index: 3771492 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0031. Min Act: -0.1700

Data Index: 7737693 (Open Web Text)

Max Activating Token Index: 949