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

Dataset: Open Web Text

Neuron 2633 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: 3.4787. Min Range: -3.4787

Max Act: 3.4787. Min Act: -0.1700

Data Index: 1736429 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.3676. Min Act: -0.1700

Data Index: 7689851 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.3900. Min Act: -0.1700

Data Index: 3326478 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.3226. Min Act: -0.1700

Data Index: 694693 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.3056. Min Act: -0.1700

Data Index: 1525858 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2921. Min Act: -0.1700

Data Index: 8737641 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2996. Min Act: -0.1700

Data Index: 3013774 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2997. Min Act: -0.1700

Data Index: 3401008 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2795. Min Act: -0.1700

Data Index: 134031 (Open Web Text)

Max Activating Token Index: 844

Text #9

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2728. Min Act: -0.1700

Data Index: 8706616 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2645. Min Act: -0.1700

Data Index: 7216765 (Open Web Text)

Max Activating Token Index: 928

Text #11

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2586. Min Act: -0.1700

Data Index: 1211932 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2709. Min Act: -0.1700

Data Index: 421701 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2904. Min Act: -0.1700

Data Index: 8370299 (Open Web Text)

Max Activating Token Index: 835

Text #14

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2717. Min Act: -0.1700

Data Index: 7649856 (Open Web Text)

Max Activating Token Index: 567

Text #15

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2473. Min Act: -0.1700

Data Index: 3847735 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2494. Min Act: -0.1700

Data Index: 4004776 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2512. Min Act: -0.1700

Data Index: 920458 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2534. Min Act: -0.1700

Data Index: 4439116 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.4787. Min Range: -3.4787

Max Act: 3.2435. Min Act: -0.1700

Data Index: 5163231 (Open Web Text)

Max Activating Token Index: 838