Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.8250. Min Act: -0.1700
Data Index: 701755 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.6375. Min Act: -0.1700
Data Index: 2991928 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.4500. Min Act: -0.1700
Data Index: 3935356 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.3250. Min Act: -0.1700
Data Index: 4040064 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.2938. Min Act: -0.1700
Data Index: 5934737 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.1375. Min Act: -0.1700
Data Index: 308544 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.1063. Min Act: -0.1700
Data Index: 6061752 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.0438. Min Act: -0.1700
Data Index: 126453 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.0750. Min Act: -0.1700
Data Index: 6222919 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.0750. Min Act: -0.1700
Data Index: 226308 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.0125. Min Act: -0.1700
Data Index: 8021984 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8250. Min Range: -7.8250
Max Act: 7.0125. Min Act: -0.1700
Data Index: 5247702 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9500. Min Act: -0.1700
Data Index: 655205 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9500. Min Act: -0.1700
Data Index: 4195742 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9500. Min Act: -0.1700
Data Index: 4238589 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9500. Min Act: -0.1700
Data Index: 7162845 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6877230 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.8875. Min Act: -0.1700
Data Index: 741880 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6117389 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8250. Min Range: -7.8250
Max Act: 6.9188. Min Act: -0.1700
Data Index: 203587 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19