Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.6311. Min Act: -0.1700
Data Index: 7470047 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.5061. Min Act: -0.1700
Data Index: 7492114 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.4749. Min Act: -0.1700
Data Index: 2013610 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.4436. Min Act: -0.1700
Data Index: 3955778 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.3811. Min Act: -0.1700
Data Index: 1203577 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.3186. Min Act: -0.1700
Data Index: 2013609 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2874. Min Act: -0.1700
Data Index: 4251420 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2874. Min Act: -0.1700
Data Index: 7297345 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2874. Min Act: -0.1700
Data Index: 8101886 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2561. Min Act: -0.1700
Data Index: 6951467 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2561. Min Act: -0.1700
Data Index: 313039 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2561. Min Act: -0.1700
Data Index: 1639604 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6055883 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.2249. Min Act: -0.1700
Data Index: 3092968 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1936. Min Act: -0.1700
Data Index: 1081760 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1936. Min Act: -0.1700
Data Index: 8194287 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1936. Min Act: -0.1700
Data Index: 672922 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1936. Min Act: -0.1700
Data Index: 6982117 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1936. Min Act: -0.1700
Data Index: 3567641 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6311. Min Range: -5.6311
Max Act: 5.1624. Min Act: -0.1700
Data Index: 5303406 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19