Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1008. Min Range: -6.1008
Max Act: 6.1008. Min Act: -0.1700
Data Index: 2105223 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.9445. Min Act: -0.1700
Data Index: 8536962 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.8195. Min Act: -0.1700
Data Index: 8107555 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.7258. Min Act: -0.1700
Data Index: 5165577 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.6008. Min Act: -0.1700
Data Index: 4202727 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.6008. Min Act: -0.1700
Data Index: 2763630 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.6008. Min Act: -0.1700
Data Index: 6456905 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.5695. Min Act: -0.1700
Data Index: 3023286 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.5695. Min Act: -0.1700
Data Index: 776235 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.5070. Min Act: -0.1700
Data Index: 3837728 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4445. Min Act: -0.1700
Data Index: 8055746 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4758. Min Act: -0.1700
Data Index: 1209214 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4758. Min Act: -0.1700
Data Index: 1902995 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.5070. Min Act: -0.1700
Data Index: 489851 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4445. Min Act: -0.1700
Data Index: 215810 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4445. Min Act: -0.1700
Data Index: 6963541 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.4445. Min Act: -0.1700
Data Index: 4831185 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.3820. Min Act: -0.1700
Data Index: 7155886 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.3820. Min Act: -0.1700
Data Index: 4105027 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1008. Min Range: -6.1008
Max Act: 5.3820. Min Act: -0.1700
Data Index: 2009923 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19