Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2424 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3811. Min Range: -7.3811
Max Act: 7.3811. Min Act: -0.1700
Data Index: 1693422 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3811. Min Range: -7.3811
Max Act: 7.1624. Min Act: -0.1700
Data Index: 8576564 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.8811. Min Act: -0.1700
Data Index: 310251 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.8811. Min Act: -0.1700
Data Index: 7049032 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.7874. Min Act: -0.1700
Data Index: 3152612 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.7874. Min Act: -0.1700
Data Index: 6111052 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.7874. Min Act: -0.1700
Data Index: 4702862 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.7561. Min Act: -0.1700
Data Index: 4881830 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.7874. Min Act: -0.1700
Data Index: 4122205 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6936. Min Act: -0.1700
Data Index: 6622197 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6936. Min Act: -0.1700
Data Index: 8035274 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6624. Min Act: -0.1700
Data Index: 6027095 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6624. Min Act: -0.1700
Data Index: 6000128 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6624. Min Act: -0.1700
Data Index: 7734035 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6936. Min Act: -0.1700
Data Index: 7285579 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6311. Min Act: -0.1700
Data Index: 4578153 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6624. Min Act: -0.1700
Data Index: 6719916 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.6311. Min Act: -0.1700
Data Index: 2136217 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.5999. Min Act: -0.1700
Data Index: 3732769 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3811. Min Range: -7.3811
Max Act: 6.5686. Min Act: -0.1700
Data Index: 7847745 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19