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

Dataset: Open Web Text

Neuron 2999 in Layer 3

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: 4.7127. Min Range: -4.7127

Max Act: 4.7127. Min Act: -0.1700

Data Index: 1730182 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.6110. Min Act: -0.1700

Data Index: 443567 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5931. Min Act: -0.1700

Data Index: 1562945 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5642. Min Act: -0.1700

Data Index: 3738872 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5182. Min Act: -0.1700

Data Index: 4015953 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5142. Min Act: -0.1700

Data Index: 6332224 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5176. Min Act: -0.1700

Data Index: 4896883 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5068. Min Act: -0.1700

Data Index: 2367592 (Open Web Text)

Max Activating Token Index: 293

Text #8

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5183. Min Act: -0.1700

Data Index: 5158734 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.5188. Min Act: -0.1700

Data Index: 6169678 (Open Web Text)

Max Activating Token Index: 716

Text #10

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4690. Min Act: -0.1700

Data Index: 8449060 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4553. Min Act: -0.1700

Data Index: 3754193 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4634. Min Act: -0.1700

Data Index: 6673998 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4536. Min Act: -0.1700

Data Index: 1764257 (Open Web Text)

Max Activating Token Index: 306

Text #14

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4373. Min Act: -0.1700

Data Index: 2637090 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4653. Min Act: -0.1700

Data Index: 2839462 (Open Web Text)

Max Activating Token Index: 790

Text #16

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4521. Min Act: -0.1700

Data Index: 7794839 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4212. Min Act: -0.1700

Data Index: 308348 (Open Web Text)

Max Activating Token Index: 291

Text #18

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.4286. Min Act: -0.1700

Data Index: 5124920 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.3962. Min Act: -0.1700

Data Index: 6089131 (Open Web Text)

Max Activating Token Index: 187