Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0848. Min Act: -0.1700
Data Index: 8184967 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0535. Min Act: -0.1700
Data Index: 3416668 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0535. Min Act: -0.1700
Data Index: 6106444 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0223. Min Act: -0.1700
Data Index: 5668649 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0223. Min Act: -0.1700
Data Index: 4721610 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0223. Min Act: -0.1700
Data Index: 8046238 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0848. Min Range: -5.0848
Max Act: 5.0223. Min Act: -0.1700
Data Index: 3416663 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9910. Min Act: -0.1700
Data Index: 3075785 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9910. Min Act: -0.1700
Data Index: 864827 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9910. Min Act: -0.1700
Data Index: 253937 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9910. Min Act: -0.1700
Data Index: 8777438 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9910. Min Act: -0.1700
Data Index: 1427818 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9598. Min Act: -0.1700
Data Index: 6661375 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9598. Min Act: -0.1700
Data Index: 7587916 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2192642 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2605562 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8567713 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.8973. Min Act: -0.1700
Data Index: 5425012 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.8973. Min Act: -0.1700
Data Index: 725223 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0848. Min Range: -5.0848
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8001536 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19