Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1103. Min Range: -6.1103
Max Act: 6.1103. Min Act: -0.1700
Data Index: 7082545 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1103. Min Range: -6.1103
Max Act: 6.0478. Min Act: -0.1700
Data Index: 6587925 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9853. Min Act: -0.1700
Data Index: 1501278 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9853. Min Act: -0.1700
Data Index: 5132456 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9853. Min Act: -0.1700
Data Index: 2154996 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9228. Min Act: -0.1700
Data Index: 2966844 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9228. Min Act: -0.1700
Data Index: 5542471 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8915. Min Act: -0.1700
Data Index: 6463558 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8915. Min Act: -0.1700
Data Index: 5541656 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8290. Min Act: -0.1700
Data Index: 6581439 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8290. Min Act: -0.1700
Data Index: 8656966 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8290. Min Act: -0.1700
Data Index: 476080 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7665. Min Act: -0.1700
Data Index: 7067340 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 6881252 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 6999749 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7040. Min Act: -0.1700
Data Index: 2793883 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1501277 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.6728. Min Act: -0.1700
Data Index: 1727478 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.6728. Min Act: -0.1700
Data Index: 6615111 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7040. Min Act: -0.1700
Data Index: 410913 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19