Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.1591. Min Act: -0.1700
Data Index: 4469673 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.1591. Min Act: -0.1700
Data Index: 5215538 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.1279. Min Act: -0.1700
Data Index: 8609666 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0966. Min Act: -0.1700
Data Index: 5185839 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0966. Min Act: -0.1700
Data Index: 8157674 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0966. Min Act: -0.1700
Data Index: 429032 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0654. Min Act: -0.1700
Data Index: 1046729 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0654. Min Act: -0.1700
Data Index: 4605143 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0654. Min Act: -0.1700
Data Index: 6312206 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0654. Min Act: -0.1700
Data Index: 4156472 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0654. Min Act: -0.1700
Data Index: 4907674 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0341. Min Act: -0.1700
Data Index: 5185834 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0341. Min Act: -0.1700
Data Index: 500844 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0341. Min Act: -0.1700
Data Index: 4749739 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0029. Min Act: -0.1698
Data Index: 2201185 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1591. Min Range: -5.1591
Max Act: 4.9716. Min Act: -0.1700
Data Index: 4112490 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0029. Min Act: -0.1700
Data Index: 5853353 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0029. Min Act: -0.1699
Data Index: 5187072 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1591. Min Range: -5.1591
Max Act: 5.0029. Min Act: -0.1700
Data Index: 3597638 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1591. Min Range: -5.1591
Max Act: 4.9716. Min Act: -0.1700
Data Index: 4307850 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19