Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 2586636 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 3217737 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 8814288 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 32858 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 32857 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5031814 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 1181794 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 5488174 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 6580760 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 5914177 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9870. Min Act: -0.1700
Data Index: 5020274 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9870. Min Act: -0.1700
Data Index: 7017688 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9870. Min Act: -0.1700
Data Index: 4096998 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 7053218 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9245. Min Act: -0.1700
Data Index: 167830 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8932. Min Act: -0.1700
Data Index: 1967745 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8620. Min Act: -0.1700
Data Index: 2446654 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.7995. Min Act: -0.1700
Data Index: 939708 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.7995. Min Act: -0.1700
Data Index: 4262205 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.7995. Min Act: -0.1700
Data Index: 1595581 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19