Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.7250. Min Act: -0.1700
Data Index: 5095265 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.7250. Min Act: -0.1700
Data Index: 3835149 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.5375. Min Act: -0.1700
Data Index: 6381667 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.5375. Min Act: -0.1700
Data Index: 5703625 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.4438. Min Act: -0.1700
Data Index: 8533817 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.4438. Min Act: -0.1700
Data Index: 3960283 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.4125. Min Act: -0.1700
Data Index: 8186950 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3813. Min Act: -0.1700
Data Index: 3412431 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.4125. Min Act: -0.1700
Data Index: 6227226 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3813. Min Act: -0.1700
Data Index: 6336047 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3500. Min Act: -0.1700
Data Index: 7058100 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3500. Min Act: -0.1700
Data Index: 5524573 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3500. Min Act: -0.1700
Data Index: 5388277 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3188. Min Act: -0.1700
Data Index: 3964981 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.3500. Min Act: -0.1700
Data Index: 825161 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.2875. Min Act: -0.1700
Data Index: 2020076 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.2563. Min Act: -0.1700
Data Index: 3051173 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.2563. Min Act: -0.1700
Data Index: 571899 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5655687 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7250. Min Range: -6.7250
Max Act: 6.1625. Min Act: -0.1700
Data Index: 7301040 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19