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

Dataset: Open Web Text

Neuron 688 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: 4.9529. Min Range: -4.9529

Max Act: 4.9529. Min Act: -0.1700

Data Index: 2645932 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.7797. Min Act: -0.1700

Data Index: 8415024 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.7659. Min Act: -0.1700

Data Index: 3587792 (Open Web Text)

Max Activating Token Index: 196

Text #3

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.7034. Min Act: -0.1700

Data Index: 3306071 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.7105. Min Act: -0.1700

Data Index: 4373409 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6758. Min Act: -0.1700

Data Index: 5221506 (Open Web Text)

Max Activating Token Index: 196

Text #6

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.7044. Min Act: -0.1700

Data Index: 8149061 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6691. Min Act: -0.1700

Data Index: 2869087 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6381. Min Act: -0.1700

Data Index: 3146708 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6491. Min Act: -0.1700

Data Index: 1929921 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6641. Min Act: -0.1700

Data Index: 332485 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6252. Min Act: -0.1700

Data Index: 3840238 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6143. Min Act: -0.1700

Data Index: 2807680 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6314. Min Act: -0.1700

Data Index: 4710307 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6064. Min Act: -0.1700

Data Index: 8179693 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.5913. Min Act: -0.1700

Data Index: 1648229 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6057. Min Act: -0.1700

Data Index: 3738181 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.5901. Min Act: -0.1700

Data Index: 7966052 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.6131. Min Act: -0.1700

Data Index: 6880396 (Open Web Text)

Max Activating Token Index: 140

Text #19

Max Range: 4.9529. Min Range: -4.9529

Max Act: 4.5918. Min Act: -0.1700

Data Index: 6371418 (Open Web Text)

Max Activating Token Index: 154