Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0076. Min Range: -5.0076
Max Act: 5.0076. Min Act: -0.1700
Data Index: 4820915 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.9763. Min Act: -0.1700
Data Index: 5449924 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.9763. Min Act: -0.1700
Data Index: 7002298 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.8826. Min Act: -0.1700
Data Index: 5869714 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.8826. Min Act: -0.1700
Data Index: 4211158 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.8513. Min Act: -0.1700
Data Index: 7657999 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.8201. Min Act: -0.1700
Data Index: 22818 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 7677434 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 7234292 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 5506525 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 1449931 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 5237586 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7888. Min Act: -0.1700
Data Index: 2199162 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7576. Min Act: -0.1700
Data Index: 615544 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7576. Min Act: -0.1700
Data Index: 5652227 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.6951. Min Act: -0.1700
Data Index: 8344928 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7263. Min Act: -0.1700
Data Index: 8739555 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.7263. Min Act: -0.1700
Data Index: 6932411 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.6951. Min Act: -0.1700
Data Index: 6755008 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0076. Min Range: -5.0076
Max Act: 4.6951. Min Act: -0.1700
Data Index: 2974745 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19