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

Dataset: Open Web Text

Neuron 1009 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: 3.2735. Min Range: -3.2735

Max Act: 3.2735. Min Act: -0.1700

Data Index: 2670992 (Open Web Text)

Max Activating Token Index: 990

Text #1

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2662. Min Act: -0.1700

Data Index: 5616258 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2576. Min Act: -0.1700

Data Index: 2352248 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2100. Min Act: -0.1700

Data Index: 5749312 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2121. Min Act: -0.1700

Data Index: 1267692 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1921. Min Act: -0.1700

Data Index: 1845230 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1592212 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1511905 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1809. Min Act: -0.1700

Data Index: 5473448 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1878. Min Act: -0.1700

Data Index: 8343935 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1800. Min Act: -0.1700

Data Index: 5798214 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1862. Min Act: -0.1700

Data Index: 2392570 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1918. Min Act: -0.1700

Data Index: 8592043 (Open Web Text)

Max Activating Token Index: 449

Text #13

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1723595 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1788. Min Act: -0.1700

Data Index: 5483718 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1621. Min Act: -0.1700

Data Index: 24985 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1486. Min Act: -0.1700

Data Index: 5480465 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1449. Min Act: -0.1700

Data Index: 4728928 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1566. Min Act: -0.1700

Data Index: 5640349 (Open Web Text)

Max Activating Token Index: 492

Text #19

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1438. Min Act: -0.1700

Data Index: 825381 (Open Web Text)

Max Activating Token Index: 875