Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.8288. Min Act: -0.1700
Data Index: 3375891 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7976. Min Act: -0.1700
Data Index: 3375888 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7351. Min Act: -0.1700
Data Index: 5183558 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7351. Min Act: -0.1700
Data Index: 3375887 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7291851 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7038. Min Act: -0.1700
Data Index: 3007442 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.7038. Min Act: -0.1700
Data Index: 1798367 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1623703 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4776813 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4952863 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6413. Min Act: -0.1700
Data Index: 2125225 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 440031 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 4499855 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7771431 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5882151 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3375886 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.5788. Min Act: -0.1700
Data Index: 4776810 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5938420 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.5788. Min Act: -0.1700
Data Index: 3375882 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8288. Min Range: -5.8288
Max Act: 5.5788. Min Act: -0.1700
Data Index: 3375885 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19