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

Dataset: Open Web Text

Neuron 1838 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: 3.9648. Min Range: -3.9648

Max Act: 3.9648. Min Act: -0.1700

Data Index: 7150235 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.9174. Min Act: -0.1700

Data Index: 2046924 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.9044. Min Act: -0.1700

Data Index: 448353 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8392. Min Act: -0.1700

Data Index: 445663 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8422. Min Act: -0.1700

Data Index: 5845557 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8331. Min Act: -0.1700

Data Index: 2868025 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8082. Min Act: -0.1700

Data Index: 4565193 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8088. Min Act: -0.1700

Data Index: 5209820 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7927. Min Act: -0.1700

Data Index: 6098209 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.8072. Min Act: -0.1700

Data Index: 1563314 (Open Web Text)

Max Activating Token Index: 531

Text #10

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7573. Min Act: -0.1700

Data Index: 975619 (Open Web Text)

Max Activating Token Index: 293

Text #11

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7615. Min Act: -0.1700

Data Index: 5101157 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7711. Min Act: -0.1700

Data Index: 6034847 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7608. Min Act: -0.1700

Data Index: 8467133 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7537. Min Act: -0.1700

Data Index: 767317 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7831. Min Act: -0.1700

Data Index: 3210276 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7647. Min Act: -0.1700

Data Index: 4646500 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7542. Min Act: -0.1700

Data Index: 4675841 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7542. Min Act: -0.1700

Data Index: 6312909 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 3.9648. Min Range: -3.9648

Max Act: 3.7136. Min Act: -0.1700

Data Index: 3175444 (Open Web Text)

Max Activating Token Index: 719