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

Dataset: Open Web Text

Neuron 2900 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: 4.7150. Min Range: -4.7150

Max Act: 4.7150. Min Act: -0.1700

Data Index: 7478475 (Open Web Text)

Max Activating Token Index: 997

Text #1

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.6549. Min Act: -0.1700

Data Index: 7064060 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.5657. Min Act: -0.1700

Data Index: 8429429 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.5454. Min Act: -0.1700

Data Index: 6150368 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.5275. Min Act: -0.1700

Data Index: 5855805 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4952. Min Act: -0.1700

Data Index: 5085151 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4683. Min Act: -0.1700

Data Index: 5412708 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4683. Min Act: -0.1700

Data Index: 2533006 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4124. Min Act: -0.1700

Data Index: 3847212 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4465. Min Act: -0.1700

Data Index: 4463247 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4572. Min Act: -0.1700

Data Index: 4086765 (Open Web Text)

Max Activating Token Index: 547

Text #11

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.3905. Min Act: -0.1700

Data Index: 31520 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4127. Min Act: -0.1700

Data Index: 7520520 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4193. Min Act: -0.1700

Data Index: 6433315 (Open Web Text)

Max Activating Token Index: 684

Text #14

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4258. Min Act: -0.1700

Data Index: 155054 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4088. Min Act: -0.1700

Data Index: 1513536 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4202. Min Act: -0.1700

Data Index: 2778601 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4142. Min Act: -0.1700

Data Index: 4225667 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.4081. Min Act: -0.1700

Data Index: 3739538 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 4.7150. Min Range: -4.7150

Max Act: 4.3734. Min Act: -0.1700

Data Index: 6442479 (Open Web Text)

Max Activating Token Index: 491