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

Dataset: Open Web Text

Neuron 508 in Layer 5

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: 5.0122. Min Range: -5.0122

Max Act: 5.0122. Min Act: -0.1700

Data Index: 1868242 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9912. Min Act: -0.1700

Data Index: 5939643 (Open Web Text)

Max Activating Token Index: 567

Text #2

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9980. Min Act: -0.1700

Data Index: 1691045 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9816. Min Act: -0.1700

Data Index: 3075747 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9642. Min Act: -0.1700

Data Index: 6357365 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9572. Min Act: -0.1700

Data Index: 99646 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9356. Min Act: -0.1700

Data Index: 5132446 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9037. Min Act: -0.1700

Data Index: 2286645 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9151. Min Act: -0.1700

Data Index: 2018209 (Open Web Text)

Max Activating Token Index: 888

Text #9

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9094. Min Act: -0.1700

Data Index: 4906369 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8981. Min Act: -0.1700

Data Index: 1796276 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9364. Min Act: -0.1700

Data Index: 4010857 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9095. Min Act: -0.1700

Data Index: 1796272 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9457. Min Act: -0.1700

Data Index: 7004654 (Open Web Text)

Max Activating Token Index: 585

Text #14

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.9107. Min Act: -0.1700

Data Index: 950197 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8949. Min Act: -0.1700

Data Index: 4423039 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8896. Min Act: -0.1700

Data Index: 3646466 (Open Web Text)

Max Activating Token Index: 373

Text #17

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8855. Min Act: -0.1700

Data Index: 1905992 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8601. Min Act: -0.1700

Data Index: 2797767 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 5.0122. Min Range: -5.0122

Max Act: 4.8682. Min Act: -0.1700

Data Index: 5938121 (Open Web Text)

Max Activating Token Index: 519