Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.4189. Min Act: -0.1700
Data Index: 333894 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.3251. Min Act: -0.1700
Data Index: 422865 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.3876. Min Act: -0.1700
Data Index: 755966 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2626. Min Act: -0.1700
Data Index: 8329121 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2939. Min Act: -0.1700
Data Index: 3754343 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2626. Min Act: -0.1700
Data Index: 8751346 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2626. Min Act: -0.1700
Data Index: 8810524 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2626. Min Act: -0.1700
Data Index: 4976413 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2001. Min Act: -0.1700
Data Index: 8110585 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.1376. Min Act: -0.1700
Data Index: 6971938 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.2001. Min Act: -0.1700
Data Index: 5544575 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.1689. Min Act: -0.1700
Data Index: 8607555 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.1376. Min Act: -0.1700
Data Index: 7738606 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.1376. Min Act: -0.1700
Data Index: 2700836 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0751. Min Act: -0.1700
Data Index: 1717796 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0751. Min Act: -0.1700
Data Index: 4344909 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0439. Min Act: -0.1700
Data Index: 2063965 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0751. Min Act: -0.1700
Data Index: 6402815 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0439. Min Act: -0.1700
Data Index: 2700837 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4189. Min Range: -7.4189
Max Act: 7.0439. Min Act: -0.1700
Data Index: 6294298 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19