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

Dataset: Open Web Text

Neuron 790 in Layer 3

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: 4.0904. Min Range: -4.0904

Max Act: 4.0904. Min Act: -0.1700

Data Index: 5829827 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0638. Min Act: -0.1700

Data Index: 5829826 (Open Web Text)

Max Activating Token Index: 989

Text #2

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0399. Min Act: -0.1700

Data Index: 2655139 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0535. Min Act: -0.1700

Data Index: 5106203 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0463. Min Act: -0.1700

Data Index: 7026689 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0259. Min Act: -0.1700

Data Index: 7262801 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9894. Min Act: -0.1700

Data Index: 2481714 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0090. Min Act: -0.1700

Data Index: 2670582 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9938. Min Act: -0.1700

Data Index: 2985070 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0135. Min Act: -0.1700

Data Index: 6836226 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9532. Min Act: -0.1700

Data Index: 1120522 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9900. Min Act: -0.1700

Data Index: 50886 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9617. Min Act: -0.1700

Data Index: 5678147 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9903. Min Act: -0.1700

Data Index: 1554367 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9737. Min Act: -0.1700

Data Index: 7195732 (Open Web Text)

Max Activating Token Index: 346

Text #15

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9766. Min Act: -0.1700

Data Index: 611336 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 4.0904. Min Range: -4.0904

Max Act: 4.0021. Min Act: -0.1700

Data Index: 2649956 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9380. Min Act: -0.1700

Data Index: 6288231 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9628. Min Act: -0.1700

Data Index: 3545092 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 4.0904. Min Range: -4.0904

Max Act: 3.9449. Min Act: -0.1700

Data Index: 2347888 (Open Web Text)

Max Activating Token Index: 225