Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4614 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.7881. Min Act: -0.1700
Data Index: 5282070 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.7256. Min Act: -0.1700
Data Index: 8770626 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6943. Min Act: -0.1700
Data Index: 7866980 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6943. Min Act: -0.1700
Data Index: 4390614 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.5693. Min Act: -0.1700
Data Index: 6140235 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6006. Min Act: -0.1700
Data Index: 6671881 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6006. Min Act: -0.1700
Data Index: 6093594 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6006. Min Act: -0.1700
Data Index: 1187403 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6006. Min Act: -0.1700
Data Index: 5059435 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.6006. Min Act: -0.1700
Data Index: 3903446 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.5693. Min Act: -0.1700
Data Index: 877451 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.5693. Min Act: -0.1700
Data Index: 7214273 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.5068. Min Act: -0.1700
Data Index: 4826758 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.4756. Min Act: -0.1700
Data Index: 8192256 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.4131. Min Act: -0.1700
Data Index: 3960775 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.4131. Min Act: -0.1700
Data Index: 4599379 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.4131. Min Act: -0.1700
Data Index: 5153580 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.3818. Min Act: -0.1700
Data Index: 1263941 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.3818. Min Act: -0.1700
Data Index: 1965062 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7881. Min Range: -7.7881
Max Act: 7.3818. Min Act: -0.1700
Data Index: 4399405 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19