Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.9967. Min Act: -0.1700
Data Index: 928043 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.9967. Min Act: -0.1700
Data Index: 1101332 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.9342. Min Act: -0.1700
Data Index: 1475611 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.8717. Min Act: -0.1700
Data Index: 2939400 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.7154. Min Act: -0.1700
Data Index: 5689937 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.7154. Min Act: -0.1700
Data Index: 4149370 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.6217. Min Act: -0.1700
Data Index: 975729 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5904. Min Act: -0.1700
Data Index: 6788650 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5592. Min Act: -0.1700
Data Index: 1479511 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5592. Min Act: -0.1700
Data Index: 6320853 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5592. Min Act: -0.1700
Data Index: 3093981 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5592. Min Act: -0.1700
Data Index: 6419414 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5592. Min Act: -0.1700
Data Index: 4384868 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.5904. Min Act: -0.1700
Data Index: 448786 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4967. Min Act: -0.1700
Data Index: 3397288 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4967. Min Act: -0.1700
Data Index: 2654960 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4967. Min Act: -0.1700
Data Index: 448782 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4967. Min Act: -0.1700
Data Index: 1190098 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4342. Min Act: -0.1700
Data Index: 5530748 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9967. Min Range: -7.9967
Max Act: 7.4342. Min Act: -0.1700
Data Index: 422434 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19