Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1283 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0583. Min Range: -6.0583
Max Act: 6.0583. Min Act: -0.1700
Data Index: 2388527 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.9958. Min Act: -0.1700
Data Index: 8754510 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3688714 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.9333. Min Act: -0.1700
Data Index: 6510428 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.9021. Min Act: -0.1700
Data Index: 6950360 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5770074 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7863450 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1562449 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7771. Min Act: -0.1700
Data Index: 6950361 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.8083. Min Act: -0.1700
Data Index: 6516600 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7458. Min Act: -0.1700
Data Index: 7034964 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7458. Min Act: -0.1700
Data Index: 6516599 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5717031 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7458. Min Act: -0.1700
Data Index: 7502443 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7458. Min Act: -0.1700
Data Index: 2219753 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7146. Min Act: -0.1700
Data Index: 4413367 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7146. Min Act: -0.1700
Data Index: 1768919 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7146. Min Act: -0.1700
Data Index: 3437727 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.7146. Min Act: -0.1700
Data Index: 728219 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0583. Min Range: -6.0583
Max Act: 5.6833. Min Act: -0.1700
Data Index: 3879009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19