Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6747. Min Act: -0.1700
Data Index: 4144485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6266. Min Act: -0.1700
Data Index: 5232530 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6266. Min Act: -0.1700
Data Index: 3442210 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6105. Min Act: -0.1700
Data Index: 1877215 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6266. Min Act: -0.1700
Data Index: 2997358 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6266. Min Act: -0.1700
Data Index: 3548969 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5944. Min Act: -0.1700
Data Index: 7778656 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.6105. Min Act: -0.1700
Data Index: 8416070 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5783. Min Act: -0.1700
Data Index: 349751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5783. Min Act: -0.1700
Data Index: 2347456 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5622. Min Act: -0.1700
Data Index: 7485652 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 5152971 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5783. Min Act: -0.1700
Data Index: 2315657 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5622. Min Act: -0.1700
Data Index: 5073239 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 7726222 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5622. Min Act: -0.1700
Data Index: 5372645 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 17645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 2568811 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 1329936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6747. Min Range: -2.6747
Max Act: 2.5461. Min Act: -0.1700
Data Index: 4532557 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19