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

Dataset: Open Web Text

Neuron 349 in Layer 0

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: 3.4666. Min Range: -3.4666

Max Act: 3.4666. Min Act: -0.1700

Data Index: 6305700 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3988. Min Act: -0.1700

Data Index: 4032114 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3763. Min Act: -0.1700

Data Index: 4589708 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3756. Min Act: -0.1700

Data Index: 5447509 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3835. Min Act: -0.1700

Data Index: 2283054 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3693. Min Act: -0.1700

Data Index: 6201421 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3284. Min Act: -0.1700

Data Index: 2049803 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3309. Min Act: -0.1700

Data Index: 8763133 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3389. Min Act: -0.1700

Data Index: 5629055 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3143. Min Act: -0.1700

Data Index: 6474138 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3104. Min Act: -0.1700

Data Index: 1571466 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3212. Min Act: -0.1700

Data Index: 2125107 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.3063. Min Act: -0.1700

Data Index: 7370599 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2941. Min Act: -0.1700

Data Index: 2236759 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2841. Min Act: -0.1700

Data Index: 5915625 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2930. Min Act: -0.1700

Data Index: 6582760 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2655. Min Act: -0.1700

Data Index: 2820128 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2719. Min Act: -0.1700

Data Index: 6901216 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2749. Min Act: -0.1700

Data Index: 7909651 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.4666. Min Range: -3.4666

Max Act: 3.2567. Min Act: -0.1700

Data Index: 6340765 (Open Web Text)

Max Activating Token Index: 3