Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3847. Min Act: -0.1700
Data Index: 6297367 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3534. Min Act: -0.1700
Data Index: 564721 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3534. Min Act: -0.1700
Data Index: 5400952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3220. Min Act: -0.1700
Data Index: 39303 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3377. Min Act: -0.1700
Data Index: 165907 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3220. Min Act: -0.1700
Data Index: 4470707 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3063. Min Act: -0.1700
Data Index: 1994681 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3063. Min Act: -0.1700
Data Index: 6477878 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3063. Min Act: -0.1700
Data Index: 7997162 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.3063. Min Act: -0.1700
Data Index: 7889101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2906. Min Act: -0.1700
Data Index: 2529836 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2906. Min Act: -0.1700
Data Index: 7423440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2906. Min Act: -0.1700
Data Index: 4115671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2749. Min Act: -0.1700
Data Index: 3843806 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2749. Min Act: -0.1700
Data Index: 2902053 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2749. Min Act: -0.1700
Data Index: 8807551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2749. Min Act: -0.1700
Data Index: 2736681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2749. Min Act: -0.1700
Data Index: 1060891 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2592. Min Act: -0.1700
Data Index: 563821 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3847. Min Range: -3.3847
Max Act: 3.2592. Min Act: -0.1700
Data Index: 279007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19