Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.8050. Min Act: -0.1700
Data Index: 260086 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.8050. Min Act: -0.1700
Data Index: 7558947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.6485. Min Act: -0.1700
Data Index: 2574443 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.6173. Min Act: -0.1700
Data Index: 6831282 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.6173. Min Act: -0.1700
Data Index: 7735657 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5860. Min Act: -0.1660
Data Index: 6787162 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5860. Min Act: -0.1700
Data Index: 7230272 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5860. Min Act: -0.1700
Data Index: 2273011 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5546. Min Act: -0.1700
Data Index: 6576653 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5546. Min Act: -0.1700
Data Index: 8111322 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5546. Min Act: -0.1700
Data Index: 3030135 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 5108242 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 7581705 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6692617 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 2341324 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6648198 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6787170 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6787161 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6787168 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8050. Min Range: -3.8050
Max Act: 3.4920. Min Act: -0.1700
Data Index: 1003516 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19