Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 405 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.4140. Min Act: -0.1700
Data Index: 6132470 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.3515. Min Act: -0.1700
Data Index: 7369731 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.3515. Min Act: -0.1700
Data Index: 8094212 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2265. Min Act: -0.1700
Data Index: 7866932 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1952. Min Act: -0.1700
Data Index: 6479861 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1327. Min Act: -0.1700
Data Index: 2387045 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7942305 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 8207305 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 1423949 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 4640573 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 5505899 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0390. Min Act: -0.1700
Data Index: 4056735 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0390. Min Act: -0.1700
Data Index: 3008595 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0077. Min Act: -0.1700
Data Index: 4908584 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1905856 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4140. Min Range: -6.4140
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3076820 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4140. Min Range: -6.4140
Max Act: 5.9765. Min Act: -0.1700
Data Index: 6263470 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4140. Min Range: -6.4140
Max Act: 5.9765. Min Act: -0.1700
Data Index: 1484389 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4140. Min Range: -6.4140
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3000380 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4140. Min Range: -6.4140
Max Act: 5.9452. Min Act: -0.1700
Data Index: 5044210 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19