Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.8360. Min Act: -0.1700
Data Index: 6382730 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.7735. Min Act: -0.1700
Data Index: 8282941 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.7110. Min Act: -0.1700
Data Index: 1408160 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.7110. Min Act: -0.1700
Data Index: 6282797 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.6485. Min Act: -0.1700
Data Index: 5941786 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.6485. Min Act: -0.1700
Data Index: 2418360 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.6172. Min Act: -0.1700
Data Index: 4323828 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5860. Min Act: -0.1700
Data Index: 6674840 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5860. Min Act: -0.1700
Data Index: 6993993 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5547. Min Act: -0.1700
Data Index: 2076360 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5235. Min Act: -0.1700
Data Index: 3341891 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5075173 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5235. Min Act: -0.1700
Data Index: 4626296 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5235. Min Act: -0.1700
Data Index: 1610838 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5235. Min Act: -0.1700
Data Index: 766667 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5703108 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 7986674 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5235. Min Act: -0.1700
Data Index: 7114889 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 3204953 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5804449 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19