Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.3747. Min Act: -0.1700
Data Index: 6396219 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.2184. Min Act: -0.1700
Data Index: 4366594 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9684. Min Act: -0.1700
Data Index: 6396223 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9059. Min Act: -0.1700
Data Index: 1372821 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.8747. Min Act: -0.1700
Data Index: 2751789 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.8122. Min Act: -0.1700
Data Index: 837209 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7497. Min Act: -0.1700
Data Index: 1230716 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 1414577 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 6180939 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5309. Min Act: -0.1700
Data Index: 6396222 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1512980 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5309. Min Act: -0.1700
Data Index: 2043283 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 5635033 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 5343894 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 2596070 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5309. Min Act: -0.1700
Data Index: 4786838 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4684. Min Act: -0.1700
Data Index: 3281854 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4684. Min Act: -0.1700
Data Index: 1870046 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3747. Min Act: -0.1700
Data Index: 5653166 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3434. Min Act: -0.1700
Data Index: 2530505 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19