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

Dataset: Open Web Text

Neuron 756 in Layer 6

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: 3.2007. Min Range: -3.2007

Max Act: 3.2007. Min Act: -0.1700

Data Index: 836189 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 3.2007. Min Range: -3.2007

Max Act: 3.1081. Min Act: -0.1700

Data Index: 8608943 (Open Web Text)

Max Activating Token Index: 935

Text #2

Max Range: 3.2007. Min Range: -3.2007

Max Act: 3.0768. Min Act: -0.1700

Data Index: 8089903 (Open Web Text)

Max Activating Token Index: 723

Text #3

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9919. Min Act: -0.1700

Data Index: 615908 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 3.2007. Min Range: -3.2007

Max Act: 3.0133. Min Act: -0.1700

Data Index: 7315880 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9789. Min Act: -0.1700

Data Index: 8542135 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9596. Min Act: -0.1700

Data Index: 4155671 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9490. Min Act: -0.1700

Data Index: 7335686 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9419. Min Act: -0.1700

Data Index: 2855139 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9184. Min Act: -0.1700

Data Index: 6088533 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9196. Min Act: -0.1700

Data Index: 2654392 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9305. Min Act: -0.1700

Data Index: 1686636 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9061. Min Act: -0.1700

Data Index: 1400841 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.9021. Min Act: -0.1700

Data Index: 1607622 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8950. Min Act: -0.1700

Data Index: 162321 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8897. Min Act: -0.1700

Data Index: 1764453 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8872. Min Act: -0.1700

Data Index: 2098774 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8937. Min Act: -0.1700

Data Index: 5786166 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8784. Min Act: -0.1700

Data Index: 5700043 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 3.2007. Min Range: -3.2007

Max Act: 2.8764. Min Act: -0.1700

Data Index: 2446527 (Open Web Text)

Max Activating Token Index: 978