Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.2720. Min Act: -0.1700
Data Index: 918427 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1620. Min Act: -0.1700
Data Index: 1319535 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1462. Min Act: -0.1700
Data Index: 5851748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1305. Min Act: -0.1700
Data Index: 5242015 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1462. Min Act: -0.1700
Data Index: 7948234 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1462. Min Act: -0.1700
Data Index: 6438564 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1305. Min Act: -0.1700
Data Index: 7539718 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1147. Min Act: -0.1700
Data Index: 8400047 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0990. Min Act: -0.1700
Data Index: 83547 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7936164 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 5724584 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0990. Min Act: -0.1700
Data Index: 5617676 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 6116716 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 8190392 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 4456397 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 2394164 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7869013 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 327277 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 6315833 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0674. Min Act: -0.1700
Data Index: 5007555 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19