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

Dataset: Open Web Text

Neuron 2584 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: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1696

Data Index: 1922778 (Open Web Text)

Max Activating Token Index: 1

Text #1

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1700

Data Index: 8524747 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1700

Data Index: 8378355 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1700

Data Index: 5505993 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1698

Data Index: 6668513 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1696

Data Index: 7481159 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1639

Data Index: 79902 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1700

Data Index: 8093165 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0442. Min Act: -0.1696

Data Index: 1212545 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0249. Min Act: -0.1700

Data Index: 324711 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0268. Min Act: -0.1700

Data Index: 5276299 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0175. Min Act: -0.1700

Data Index: 3964903 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0185. Min Act: -0.1684

Data Index: 479619 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0117. Min Act: -0.1700

Data Index: 5994303 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0011. Min Act: -0.1700

Data Index: 5213920 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.0442. Min Range: -2.0442

Max Act: 1.9988. Min Act: -0.1700

Data Index: 113749 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0061. Min Act: -0.1690

Data Index: 3103776 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.0442. Min Range: -2.0442

Max Act: 1.9952. Min Act: -0.1694

Data Index: 6273020 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.0442. Min Range: -2.0442

Max Act: 1.9868. Min Act: -0.1696

Data Index: 2198119 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.0442. Min Range: -2.0442

Max Act: 2.0033. Min Act: -0.1697

Data Index: 5996703 (Open Web Text)

Max Activating Token Index: 408