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

Dataset: Open Web Text

Neuron 28 in Layer 2

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: 4.3008. Min Range: -4.3008

Max Act: 4.3008. Min Act: -0.1700

Data Index: 7238848 (Open Web Text)

Max Activating Token Index: 728

Text #1

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.2425. Min Act: -0.1700

Data Index: 6501796 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.1992. Min Act: -0.1700

Data Index: 6146432 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.1854. Min Act: -0.1700

Data Index: 324501 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.1034. Min Act: -0.1700

Data Index: 3245256 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.1069. Min Act: -0.1700

Data Index: 8690331 (Open Web Text)

Max Activating Token Index: 821

Text #6

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.0483. Min Act: -0.1700

Data Index: 4292773 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.0453. Min Act: -0.1700

Data Index: 8690333 (Open Web Text)

Max Activating Token Index: 169

Text #8

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.0477. Min Act: -0.1700

Data Index: 7392948 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 4.3008. Min Range: -4.3008

Max Act: 4.0011. Min Act: -0.1700

Data Index: 6142401 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9942. Min Act: -0.1700

Data Index: 2588874 (Open Web Text)

Max Activating Token Index: 660

Text #11

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9779. Min Act: -0.1700

Data Index: 961047 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9610. Min Act: -0.1700

Data Index: 6744509 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9516. Min Act: -0.1700

Data Index: 6930838 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9773. Min Act: -0.1700

Data Index: 3941121 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9467. Min Act: -0.1700

Data Index: 1302707 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9694. Min Act: -0.1700

Data Index: 7565098 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9467. Min Act: -0.1700

Data Index: 6409664 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9380. Min Act: -0.1700

Data Index: 2810398 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 4.3008. Min Range: -4.3008

Max Act: 3.9006. Min Act: -0.1700

Data Index: 1709825 (Open Web Text)

Max Activating Token Index: 147