Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0512. Min Range: -9.0512
Max Act: 9.0512. Min Act: -0.1700
Data Index: 2483086 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.7387. Min Act: -0.1699
Data Index: 8230767 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.6762. Min Act: -0.1700
Data Index: 3126085 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.6137. Min Act: -0.1700
Data Index: 1769575 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.5512. Min Act: -0.1700
Data Index: 6920118 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.6137. Min Act: -0.1700
Data Index: 8363130 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.4262. Min Act: -0.1700
Data Index: 2737057 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.4887. Min Act: -0.1700
Data Index: 4393267 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.4262. Min Act: -0.1700
Data Index: 1517318 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.4262. Min Act: -0.1700
Data Index: 2948414 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.4262. Min Act: -0.1700
Data Index: 360746 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3012. Min Act: -0.1700
Data Index: 2958578 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3637. Min Act: -0.1700
Data Index: 1870831 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3012. Min Act: -0.1700
Data Index: 8533967 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3012. Min Act: -0.1700
Data Index: 1462840 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3012. Min Act: -0.1700
Data Index: 3585739 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.3012. Min Act: -0.1700
Data Index: 8292118 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.2387. Min Act: -0.1700
Data Index: 8168720 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.1762. Min Act: -0.1700
Data Index: 6464204 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0512. Min Range: -9.0512
Max Act: 8.2387. Min Act: -0.1700
Data Index: 1764236 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19