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

Dataset: Open Web Text

Neuron 2431 in Layer 6

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: 4.2396. Min Range: -4.2396

Max Act: 4.2396. Min Act: -0.1700

Data Index: 7341878 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.2362. Min Act: -0.1700

Data Index: 6291206 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.2018. Min Act: -0.1700

Data Index: 3294786 (Open Web Text)

Max Activating Token Index: 770

Text #3

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.2100. Min Act: -0.1700

Data Index: 6996083 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.1708. Min Act: -0.1700

Data Index: 1435191 (Open Web Text)

Max Activating Token Index: 791

Text #5

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.1053. Min Act: -0.1700

Data Index: 8397473 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0925. Min Act: -0.1700

Data Index: 688754 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.1149. Min Act: -0.1700

Data Index: 8029975 (Open Web Text)

Max Activating Token Index: 135

Text #8

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0984. Min Act: -0.1700

Data Index: 5442592 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0790. Min Act: -0.1700

Data Index: 6884405 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0922. Min Act: -0.1700

Data Index: 1670200 (Open Web Text)

Max Activating Token Index: 261

Text #11

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0314. Min Act: -0.1700

Data Index: 6121005 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0523. Min Act: -0.1700

Data Index: 1467586 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0572. Min Act: -0.1700

Data Index: 7677028 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0151. Min Act: -0.1700

Data Index: 454485 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0236. Min Act: -0.1700

Data Index: 8382605 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0056. Min Act: -0.1700

Data Index: 5170436 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0269. Min Act: -0.1700

Data Index: 1665789 (Open Web Text)

Max Activating Token Index: 1018

Text #18

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.9948. Min Act: -0.1700

Data Index: 1742187 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 4.2396. Min Range: -4.2396

Max Act: 4.0057. Min Act: -0.1700

Data Index: 4442674 (Open Web Text)

Max Activating Token Index: 104