Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4284. Min Range: -7.4284
Max Act: 7.4284. Min Act: -0.1700
Data Index: 8105543 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.9284. Min Act: -0.1700
Data Index: 821337 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.6159. Min Act: -0.1700
Data Index: 7699725 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.5846. Min Act: -0.1700
Data Index: 335167 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.5846. Min Act: -0.1700
Data Index: 492897 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.5534. Min Act: -0.1700
Data Index: 5343015 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.4596. Min Act: -0.1700
Data Index: 5083770 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3971. Min Act: -0.1700
Data Index: 5388886 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3971. Min Act: -0.1700
Data Index: 954152 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5048223 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3659. Min Act: -0.1700
Data Index: 3566061 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3659. Min Act: -0.1700
Data Index: 384995 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3346. Min Act: -0.1700
Data Index: 2304950 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3346. Min Act: -0.1700
Data Index: 4596259 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3034. Min Act: -0.1700
Data Index: 8508660 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3034. Min Act: -0.1700
Data Index: 1266357 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.3034. Min Act: -0.1700
Data Index: 6432720 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.2721. Min Act: -0.1700
Data Index: 366908 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1118178 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4284. Min Range: -7.4284
Max Act: 6.2721. Min Act: -0.1700
Data Index: 731195 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19