Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2309. Min Range: -2.2309
Max Act: 2.2309. Min Act: -0.1699
Data Index: 133707 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2309. Min Range: -2.2309
Max Act: 2.2309. Min Act: -0.1700
Data Index: 8091427 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2309. Min Range: -2.2309
Max Act: 2.0810. Min Act: -0.1700
Data Index: 1572699 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9459. Min Act: -0.1700
Data Index: 1280614 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9289. Min Act: -0.1698
Data Index: 8025052 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9119. Min Act: -0.1700
Data Index: 2640107 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9119. Min Act: -0.1700
Data Index: 3625744 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9119. Min Act: -0.1696
Data Index: 2660723 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9119. Min Act: -0.1700
Data Index: 5581648 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.9119. Min Act: -0.1700
Data Index: 1807567 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8949. Min Act: -0.1700
Data Index: 4318120 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8949. Min Act: -0.1700
Data Index: 1263181 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8949. Min Act: -0.1700
Data Index: 500081 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8778. Min Act: -0.1669
Data Index: 1477191 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8778. Min Act: -0.1700
Data Index: 5072026 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8607. Min Act: -0.1700
Data Index: 6818116 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8778. Min Act: -0.1699
Data Index: 2349405 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8435. Min Act: -0.1699
Data Index: 3353950 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8607. Min Act: -0.1700
Data Index: 6013936 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2309. Min Range: -2.2309
Max Act: 1.8435. Min Act: -0.1699
Data Index: 3473346 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19