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

Dataset: Open Web Text

Neuron 1376 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: 3.0589. Min Range: -3.0589

Max Act: 3.0589. Min Act: -0.1700

Data Index: 8798224 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.9667. Min Act: -0.1700

Data Index: 3072686 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.9243. Min Act: -0.1700

Data Index: 1676329 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8969. Min Act: -0.1700

Data Index: 8036722 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8808. Min Act: -0.1700

Data Index: 1588886 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8929. Min Act: -0.1700

Data Index: 1107834 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8819. Min Act: -0.1700

Data Index: 1571425 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8749. Min Act: -0.1700

Data Index: 5389654 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8648. Min Act: -0.1700

Data Index: 994652 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8718. Min Act: -0.1700

Data Index: 6175241 (Open Web Text)

Max Activating Token Index: 608

Text #10

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8275. Min Act: -0.1700

Data Index: 2950041 (Open Web Text)

Max Activating Token Index: 905

Text #11

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8261. Min Act: -0.1700

Data Index: 5598334 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8454. Min Act: -0.1700

Data Index: 99102 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8271. Min Act: -0.1700

Data Index: 4706151 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.7985. Min Act: -0.1700

Data Index: 6998201 (Open Web Text)

Max Activating Token Index: 803

Text #15

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8140. Min Act: -0.1700

Data Index: 2960204 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8148. Min Act: -0.1700

Data Index: 217913 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8103. Min Act: -0.1700

Data Index: 1768552 (Open Web Text)

Max Activating Token Index: 64

Text #18

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.8101. Min Act: -0.1700

Data Index: 5570039 (Open Web Text)

Max Activating Token Index: 83

Text #19

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.7932. Min Act: -0.1700

Data Index: 2021800 (Open Web Text)

Max Activating Token Index: 129