Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3557. Min Range: -9.3557
Max Act: 9.3557. Min Act: -0.1700
Data Index: 5131912 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3557. Min Range: -9.3557
Max Act: 9.1682. Min Act: -0.1700
Data Index: 3798954 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3557. Min Range: -9.3557
Max Act: 9.1057. Min Act: -0.1700
Data Index: 1761607 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3557. Min Range: -9.3557
Max Act: 9.0432. Min Act: -0.1700
Data Index: 5922271 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9807. Min Act: -0.1700
Data Index: 5053776 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9807. Min Act: -0.1700
Data Index: 2547382 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9807. Min Act: -0.1700
Data Index: 8560634 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9807. Min Act: -0.1700
Data Index: 6042963 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9182. Min Act: -0.1700
Data Index: 8446799 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9807. Min Act: -0.1700
Data Index: 5693312 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9182. Min Act: -0.1700
Data Index: 5406441 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9182. Min Act: -0.1700
Data Index: 5887235 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.9182. Min Act: -0.1700
Data Index: 2350900 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.8557. Min Act: -0.1700
Data Index: 6179719 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.8557. Min Act: -0.1700
Data Index: 5408940 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.7932. Min Act: -0.1700
Data Index: 5776899 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.8557. Min Act: -0.1700
Data Index: 1488275 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.7307. Min Act: -0.1700
Data Index: 5758754 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.7932. Min Act: -0.1700
Data Index: 2060051 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3557. Min Range: -9.3557
Max Act: 8.7932. Min Act: -0.1700
Data Index: 7947658 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19