Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6110. Min Range: -9.6110
Max Act: 9.6110. Min Act: -0.1700
Data Index: 4804830 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6110. Min Range: -9.6110
Max Act: 9.4860. Min Act: -0.1700
Data Index: 3751813 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6110. Min Range: -9.6110
Max Act: 9.1110. Min Act: -0.1700
Data Index: 3215855 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.9235. Min Act: -0.1700
Data Index: 964301 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.7360. Min Act: -0.1700
Data Index: 1791531 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6735. Min Act: -0.1700
Data Index: 2662154 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.5485. Min Act: -0.1700
Data Index: 4393910 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6110. Min Act: -0.1700
Data Index: 7665720 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6110. Min Act: -0.1700
Data Index: 5605195 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6735. Min Act: -0.1700
Data Index: 1130387 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6110. Min Act: -0.1700
Data Index: 150300 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.6110. Min Act: -0.1700
Data Index: 3630722 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.5485. Min Act: -0.1700
Data Index: 8142279 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4860. Min Act: -0.1700
Data Index: 2130479 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4235. Min Act: -0.1700
Data Index: 5964554 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4860. Min Act: -0.1700
Data Index: 6583259 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4860. Min Act: -0.1700
Data Index: 138002 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4235. Min Act: -0.1700
Data Index: 1331304 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4235. Min Act: -0.1700
Data Index: 5798184 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6110. Min Range: -9.6110
Max Act: 8.4235. Min Act: -0.1700
Data Index: 6780325 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19