Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5428 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.7854. Min Act: -0.1700
Data Index: 4365011 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.6604. Min Act: -0.1700
Data Index: 708416 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.5354. Min Act: -0.1700
Data Index: 4898484 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.5354. Min Act: -0.1700
Data Index: 4165387 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.4729. Min Act: -0.1700
Data Index: 3110284 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.4729. Min Act: -0.1699
Data Index: 4440978 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.4729. Min Act: -0.1699
Data Index: 4898489 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.4416. Min Act: -0.1700
Data Index: 1176983 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.3791. Min Act: -0.1700
Data Index: 8696408 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.3479. Min Act: -0.1700
Data Index: 6770094 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.3791. Min Act: -0.1698
Data Index: 4365008 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.3166. Min Act: -0.1700
Data Index: 1012096 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.2854. Min Act: -0.1700
Data Index: 4305050 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.2541. Min Act: -0.1700
Data Index: 6631820 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.1604. Min Act: -0.1700
Data Index: 8784333 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.1291. Min Act: -0.1694
Data Index: 3712919 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.1291. Min Act: -0.1700
Data Index: 2426580 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.1291. Min Act: -0.1700
Data Index: 5169025 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.0979. Min Act: -0.1700
Data Index: 8673657 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7854. Min Range: -8.7854
Max Act: 8.0666. Min Act: -0.1687
Data Index: 6082140 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19