Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.5100. Min Act: -0.1700
Data Index: 1840086 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.4788. Min Act: -0.1700
Data Index: 440034 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.4475. Min Act: -0.1700
Data Index: 3142973 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.3225. Min Act: -0.1700
Data Index: 7041831 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.2913. Min Act: -0.1700
Data Index: 5733315 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.3225. Min Act: -0.1700
Data Index: 2877203 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.2600. Min Act: -0.1700
Data Index: 715194 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1663. Min Act: -0.1700
Data Index: 5821360 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1975. Min Act: -0.1700
Data Index: 1229062 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1663. Min Act: -0.1700
Data Index: 2686752 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1038. Min Act: -0.1700
Data Index: 4914871 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.0725. Min Act: -0.1700
Data Index: 4924700 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1350. Min Act: -0.1700
Data Index: 4525506 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1038. Min Act: -0.1700
Data Index: 4299763 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.1038. Min Act: -0.1700
Data Index: 3009743 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.0413. Min Act: -0.1700
Data Index: 8660499 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.0100. Min Act: -0.1700
Data Index: 1651240 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.0413. Min Act: -0.1700
Data Index: 601873 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5100. Min Range: -7.5100
Max Act: 6.9475. Min Act: -0.1700
Data Index: 7198581 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5100. Min Range: -7.5100
Max Act: 7.0100. Min Act: -0.1700
Data Index: 3375156 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19