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

Dataset: Open Web Text

Neuron 1562 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: 3.8109. Min Range: -3.8109

Max Act: 3.8109. Min Act: -0.1700

Data Index: 6695066 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7920. Min Act: -0.1700

Data Index: 5219709 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6516. Min Act: -0.1700

Data Index: 4091676 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4992. Min Act: -0.1700

Data Index: 1183770 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4974. Min Act: -0.1700

Data Index: 8484223 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4261. Min Act: -0.1700

Data Index: 8474033 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4648. Min Act: -0.1700

Data Index: 6051880 (Open Web Text)

Max Activating Token Index: 840

Text #7

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4636. Min Act: -0.1700

Data Index: 4355419 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4431. Min Act: -0.1700

Data Index: 6949643 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4408. Min Act: -0.1700

Data Index: 4495878 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3849. Min Act: -0.1700

Data Index: 7189916 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1507965 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3972. Min Act: -0.1700

Data Index: 2848678 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4068. Min Act: -0.1700

Data Index: 8543310 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3888. Min Act: -0.1700

Data Index: 1067352 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3661. Min Act: -0.1700

Data Index: 4708864 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3880. Min Act: -0.1700

Data Index: 2188121 (Open Web Text)

Max Activating Token Index: 713

Text #17

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3587. Min Act: -0.1700

Data Index: 7986592 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3754. Min Act: -0.1700

Data Index: 6966562 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3533. Min Act: -0.1700

Data Index: 4070336 (Open Web Text)

Max Activating Token Index: 1014