Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5211 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5913590 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.7094. Min Act: -0.1700
Data Index: 8767338 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6782. Min Act: -0.1700
Data Index: 479240 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6469. Min Act: -0.1700
Data Index: 716417 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6469. Min Act: -0.1700
Data Index: 2085361 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6157. Min Act: -0.1700
Data Index: 6689812 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6157. Min Act: -0.1700
Data Index: 3901265 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5844. Min Act: -0.1700
Data Index: 5596352 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5844. Min Act: -0.1700
Data Index: 3920820 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5844. Min Act: -0.1700
Data Index: 2736074 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5844. Min Act: -0.1700
Data Index: 7390599 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5844. Min Act: -0.1700
Data Index: 5540199 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5532. Min Act: -0.1700
Data Index: 5753522 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5532. Min Act: -0.1700
Data Index: 2309227 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 234869 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 4795227 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 52624 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 1176171 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 4587968 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1700
Data Index: 5796884 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19