Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1751 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5816. Min Range: -7.5816
Max Act: 7.5816. Min Act: -0.1700
Data Index: 838432 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5816. Min Range: -7.5816
Max Act: 7.1129. Min Act: -0.1700
Data Index: 2098858 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5816. Min Range: -7.5816
Max Act: 7.1129. Min Act: -0.1700
Data Index: 2154939 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5816. Min Range: -7.5816
Max Act: 7.0191. Min Act: -0.1700
Data Index: 1237230 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5816. Min Range: -7.5816
Max Act: 7.0191. Min Act: -0.1700
Data Index: 5305126 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.9254. Min Act: -0.1700
Data Index: 3027663 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.9254. Min Act: -0.1700
Data Index: 2022136 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8941. Min Act: -0.1700
Data Index: 3802748 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8629. Min Act: -0.1700
Data Index: 5258803 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8629. Min Act: -0.1700
Data Index: 8570985 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8629. Min Act: -0.1700
Data Index: 5905185 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8316. Min Act: -0.1700
Data Index: 5398392 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8316. Min Act: -0.1700
Data Index: 860826 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8316. Min Act: -0.1700
Data Index: 1491765 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.8004. Min Act: -0.1700
Data Index: 641150 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.7691. Min Act: -0.1700
Data Index: 38287 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.7379. Min Act: -0.1700
Data Index: 7145964 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.7066. Min Act: -0.1700
Data Index: 5140722 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.7066. Min Act: -0.1700
Data Index: 2349505 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5816. Min Range: -7.5816
Max Act: 6.6754. Min Act: -0.1700
Data Index: 4763674 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19