Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.5133. Min Act: -0.1700
Data Index: 5202553 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.3883. Min Act: -0.1700
Data Index: 1419097 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.3258. Min Act: -0.1700
Data Index: 3314647 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.3570. Min Act: -0.1700
Data Index: 525884 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2633. Min Act: -0.1700
Data Index: 982743 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2633. Min Act: -0.1700
Data Index: 3802760 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2320. Min Act: -0.1700
Data Index: 7162939 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2008. Min Act: -0.1700
Data Index: 1152221 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2008. Min Act: -0.1700
Data Index: 7198245 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2320. Min Act: -0.1700
Data Index: 7849703 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.2008. Min Act: -0.1700
Data Index: 5683882 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1695. Min Act: -0.1700
Data Index: 3404525 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1383. Min Act: -0.1700
Data Index: 3918585 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1695. Min Act: -0.1700
Data Index: 3716958 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1070. Min Act: -0.1700
Data Index: 5134059 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1383. Min Act: -0.1700
Data Index: 685293 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1695. Min Act: -0.1700
Data Index: 2196754 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1383. Min Act: -0.1700
Data Index: 8262491 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1383. Min Act: -0.1700
Data Index: 4252525 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5133. Min Range: -4.5133
Max Act: 4.1383. Min Act: -0.1700
Data Index: 8633831 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19