Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 356 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.7528. Min Act: -0.1700
Data Index: 393992 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.3778. Min Act: -0.1700
Data Index: 2498183 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.2528. Min Act: -0.1700
Data Index: 5826499 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.1903. Min Act: -0.1700
Data Index: 640854 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.1903. Min Act: -0.1700
Data Index: 892604 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.1278. Min Act: -0.1700
Data Index: 7497123 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.0341. Min Act: -0.1700
Data Index: 3447870 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.0028. Min Act: -0.1700
Data Index: 7948415 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.0341. Min Act: -0.1700
Data Index: 649655 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.0653. Min Act: -0.1700
Data Index: 7107565 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9716. Min Act: -0.1700
Data Index: 3865151 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7528. Min Range: -6.7528
Max Act: 6.0028. Min Act: -0.1700
Data Index: 7708567 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9091. Min Act: -0.1700
Data Index: 5515408 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9091. Min Act: -0.1700
Data Index: 4953134 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9403. Min Act: -0.1700
Data Index: 4142022 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9403. Min Act: -0.1700
Data Index: 7486349 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9091. Min Act: -0.1700
Data Index: 875907 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.9091. Min Act: -0.1700
Data Index: 393439 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.8778. Min Act: -0.1700
Data Index: 6556280 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7528. Min Range: -6.7528
Max Act: 5.8778. Min Act: -0.1700
Data Index: 3602197 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19