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

Dataset: Open Web Text

Neuron 735 in Layer 4

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: 2.0898. Min Range: -2.0898

Max Act: 2.0898. Min Act: -0.1700

Data Index: 5901564 (Open Web Text)

Max Activating Token Index: 711

Text #1

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9999. Min Act: -0.1700

Data Index: 2731684 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9197. Min Act: -0.1700

Data Index: 1005343 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9137. Min Act: -0.1700

Data Index: 1770427 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9101. Min Act: -0.1700

Data Index: 795996 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9001. Min Act: -0.1700

Data Index: 553146 (Open Web Text)

Max Activating Token Index: 733

Text #6

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9083. Min Act: -0.1700

Data Index: 3888069 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8960. Min Act: -0.1700

Data Index: 3425770 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8667. Min Act: -0.1700

Data Index: 8672436 (Open Web Text)

Max Activating Token Index: 469

Text #9

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8781. Min Act: -0.1700

Data Index: 1976888 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8805. Min Act: -0.1700

Data Index: 2227029 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8806. Min Act: -0.1700

Data Index: 8370567 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9081. Min Act: -0.1700

Data Index: 1214446 (Open Web Text)

Max Activating Token Index: 914

Text #13

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8679. Min Act: -0.1700

Data Index: 5918839 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8602. Min Act: -0.1700

Data Index: 7823103 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8705. Min Act: -0.1700

Data Index: 2546365 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8617. Min Act: -0.1700

Data Index: 4488299 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8414. Min Act: -0.1700

Data Index: 8198211 (Open Web Text)

Max Activating Token Index: 954

Text #18

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8710. Min Act: -0.1700

Data Index: 4700566 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8621. Min Act: -0.1700

Data Index: 1516495 (Open Web Text)

Max Activating Token Index: 682