Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2001. Min Range: -9.2001
Max Act: 9.2001. Min Act: -0.1700
Data Index: 1910369 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2001. Min Range: -9.2001
Max Act: 9.0751. Min Act: -0.1700
Data Index: 8577069 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2001. Min Range: -9.2001
Max Act: 9.0751. Min Act: -0.1700
Data Index: 7195199 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2001. Min Range: -9.2001
Max Act: 9.0126. Min Act: -0.1700
Data Index: 7456746 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.9501. Min Act: -0.1700
Data Index: 2407039 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.9501. Min Act: -0.1700
Data Index: 4717718 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.8251. Min Act: -0.1700
Data Index: 7763274 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7626. Min Act: -0.1700
Data Index: 7718918 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.8251. Min Act: -0.1700
Data Index: 8327043 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.8251. Min Act: -0.1700
Data Index: 6306758 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7626. Min Act: -0.1700
Data Index: 1295468 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.8251. Min Act: -0.1700
Data Index: 2228001 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 2407037 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 6313309 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.6376. Min Act: -0.1700
Data Index: 7718916 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 2736290 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 7059301 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 7910396 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 7127325 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2001. Min Range: -9.2001
Max Act: 8.7001. Min Act: -0.1700
Data Index: 5906855 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19