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

Dataset: Open Web Text

Neuron 1300 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: 3.6089. Min Range: -3.6089

Max Act: 3.6089. Min Act: -0.1700

Data Index: 7107558 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.5710. Min Act: -0.1700

Data Index: 6242579 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.5180. Min Act: -0.1700

Data Index: 5776825 (Open Web Text)

Max Activating Token Index: 969

Text #3

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4907. Min Act: -0.1700

Data Index: 4864210 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4655. Min Act: -0.1700

Data Index: 5807112 (Open Web Text)

Max Activating Token Index: 1002

Text #5

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4471. Min Act: -0.1700

Data Index: 3876396 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4328. Min Act: -0.1700

Data Index: 3239980 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4146. Min Act: -0.1700

Data Index: 766007 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.4172. Min Act: -0.1700

Data Index: 2928067 (Open Web Text)

Max Activating Token Index: 919

Text #9

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3758. Min Act: -0.1700

Data Index: 6007789 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3837. Min Act: -0.1700

Data Index: 7063047 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3975. Min Act: -0.1700

Data Index: 5370523 (Open Web Text)

Max Activating Token Index: 997

Text #12

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3895. Min Act: -0.1700

Data Index: 1683706 (Open Web Text)

Max Activating Token Index: 648

Text #13

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3606. Min Act: -0.1700

Data Index: 6738166 (Open Web Text)

Max Activating Token Index: 987

Text #14

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3769. Min Act: -0.1700

Data Index: 1640780 (Open Web Text)

Max Activating Token Index: 964

Text #15

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3643. Min Act: -0.1700

Data Index: 680060 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3862. Min Act: -0.1700

Data Index: 6060856 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3769. Min Act: -0.1700

Data Index: 1500245 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3519. Min Act: -0.1700

Data Index: 8727990 (Open Web Text)

Max Activating Token Index: 701

Text #19

Max Range: 3.6089. Min Range: -3.6089

Max Act: 3.3577. Min Act: -0.1700

Data Index: 3241950 (Open Web Text)

Max Activating Token Index: 981