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

Dataset: Open Web Text

Neuron 1370 in Layer 1

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: 1.2605. Min Range: -1.2605

Max Act: 1.2605. Min Act: -0.1700

Data Index: 5843815 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.2267. Min Act: -0.1698

Data Index: 8604042 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.2035. Min Act: -0.1696

Data Index: 4434293 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1848. Min Act: -0.1698

Data Index: 1517973 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1656. Min Act: -0.1700

Data Index: 4187755 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1726. Min Act: -0.1700

Data Index: 5109435 (Open Web Text)

Max Activating Token Index: 557

Text #6

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1727. Min Act: -0.1700

Data Index: 2410616 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1680. Min Act: -0.1700

Data Index: 4157994 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1685. Min Act: -0.1696

Data Index: 5922997 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1614. Min Act: -0.1700

Data Index: 1155896 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1665. Min Act: -0.1700

Data Index: 3387751 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1581. Min Act: -0.1700

Data Index: 7678454 (Open Web Text)

Max Activating Token Index: 322

Text #12

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1537. Min Act: -0.1700

Data Index: 3789723 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1600. Min Act: -0.1700

Data Index: 51491 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1553. Min Act: -0.1696

Data Index: 1330366 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1550. Min Act: -0.1691

Data Index: 4373218 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1665. Min Act: -0.1700

Data Index: 8689858 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1547. Min Act: -0.1699

Data Index: 3609026 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1505. Min Act: -0.1700

Data Index: 285790 (Open Web Text)

Max Activating Token Index: 651

Text #19

Max Range: 1.2605. Min Range: -1.2605

Max Act: 1.1485. Min Act: -0.1700

Data Index: 605261 (Open Web Text)

Max Activating Token Index: 453