Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5895 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0567. Min Range: -6.0567
Max Act: 6.0567. Min Act: -0.1700
Data Index: 2931045 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0567. Min Range: -6.0567
Max Act: 6.0567. Min Act: -0.1700
Data Index: 4710189 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0567. Min Range: -6.0567
Max Act: 6.0567. Min Act: -0.1700
Data Index: 684196 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9630. Min Act: -0.1700
Data Index: 8631728 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9005. Min Act: -0.1700
Data Index: 3976912 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9317. Min Act: -0.1700
Data Index: 5963491 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9005. Min Act: -0.1700
Data Index: 5204844 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9005. Min Act: -0.1700
Data Index: 7533195 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.9005. Min Act: -0.1700
Data Index: 4306969 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8380. Min Act: -0.1700
Data Index: 6457943 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8692. Min Act: -0.1700
Data Index: 8366828 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8380. Min Act: -0.1700
Data Index: 246744 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8380. Min Act: -0.1700
Data Index: 246745 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8067. Min Act: -0.1700
Data Index: 1193421 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.8067. Min Act: -0.1700
Data Index: 939127 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.7755. Min Act: -0.1700
Data Index: 3796081 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.7755. Min Act: -0.1700
Data Index: 804664 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.7755. Min Act: -0.1700
Data Index: 4617277 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.7442. Min Act: -0.1700
Data Index: 6328205 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0567. Min Range: -6.0567
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5738766 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19