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

Dataset: Open Web Text

Neuron 2533 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: 6.0927. Min Range: -6.0927

Max Act: 6.0927. Min Act: -0.1700

Data Index: 1796065 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.7104. Min Act: -0.1611

Data Index: 1796088 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.5975. Min Act: -0.1700

Data Index: 4354041 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.5094. Min Act: -0.1700

Data Index: 4354017 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.4583. Min Act: -0.1692

Data Index: 7772052 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.4406. Min Act: -0.1700

Data Index: 5251221 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.4251. Min Act: -0.1700

Data Index: 5202148 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.4319. Min Act: -0.1308

Data Index: 4354033 (Open Web Text)

Max Activating Token Index: 679

Text #8

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.3695. Min Act: -0.1699

Data Index: 6058874 (Open Web Text)

Max Activating Token Index: 607

Text #9

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.3568. Min Act: -0.1691

Data Index: 6242655 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.1687. Min Act: -0.1700

Data Index: 6242658 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.1266. Min Act: -0.1700

Data Index: 2570221 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.0698. Min Act: -0.1590

Data Index: 5202161 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.0792. Min Act: -0.1699

Data Index: 5202146 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.0441. Min Act: -0.1700

Data Index: 5307798 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.0739. Min Act: -0.1696

Data Index: 5202162 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 6.0927. Min Range: -6.0927

Max Act: 5.0060. Min Act: -0.1663

Data Index: 5428482 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 6.0927. Min Range: -6.0927

Max Act: 4.9711. Min Act: -0.1666

Data Index: 5202165 (Open Web Text)

Max Activating Token Index: 89

Text #18

Max Range: 6.0927. Min Range: -6.0927

Max Act: 4.9560. Min Act: -0.1700

Data Index: 5513585 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 6.0927. Min Range: -6.0927

Max Act: 4.9882. Min Act: -0.1700

Data Index: 2249080 (Open Web Text)

Max Activating Token Index: 12