Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5855. Min Act: -0.1700
Data Index: 1292483 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5855. Min Act: -0.1700
Data Index: 1698734 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5542. Min Act: -0.1700
Data Index: 3758992 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5230. Min Act: -0.1700
Data Index: 4016918 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5230. Min Act: -0.1700
Data Index: 697854 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5230. Min Act: -0.1700
Data Index: 2115701 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5230. Min Act: -0.1700
Data Index: 4484254 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.5230. Min Act: -0.1700
Data Index: 8157541 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.4605. Min Act: -0.1700
Data Index: 4789318 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.4292. Min Act: -0.1700
Data Index: 6885840 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3980. Min Act: -0.1700
Data Index: 3933718 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3667. Min Act: -0.1700
Data Index: 1304195 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3667. Min Act: -0.1700
Data Index: 3203188 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3667. Min Act: -0.1700
Data Index: 958800 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3355. Min Act: -0.1700
Data Index: 1702246 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3355. Min Act: -0.1700
Data Index: 7940441 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.3042. Min Act: -0.1700
Data Index: 1405831 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.2730. Min Act: -0.1700
Data Index: 815185 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.2730. Min Act: -0.1700
Data Index: 4621848 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5855. Min Range: -6.5855
Max Act: 6.2730. Min Act: -0.1700
Data Index: 3231050 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19