Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0864. Min Range: -6.0864
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1673129 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0864. Min Range: -6.0864
Max Act: 6.0864. Min Act: -0.1700
Data Index: 2029459 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0864. Min Range: -6.0864
Max Act: 6.0864. Min Act: -0.1700
Data Index: 7423724 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.9614. Min Act: -0.1700
Data Index: 8065677 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.9614. Min Act: -0.1700
Data Index: 3357611 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.9614. Min Act: -0.1700
Data Index: 4778776 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8989. Min Act: -0.1700
Data Index: 4427704 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8677. Min Act: -0.1700
Data Index: 6031870 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8677. Min Act: -0.1700
Data Index: 1985712 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8677. Min Act: -0.1700
Data Index: 738450 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8052. Min Act: -0.1700
Data Index: 4580791 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.8052. Min Act: -0.1700
Data Index: 685777 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 988615 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 3426153 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 3583046 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 2085551 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 2159884 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7427. Min Act: -0.1700
Data Index: 6751169 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7739. Min Act: -0.1700
Data Index: 5078564 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0864. Min Range: -6.0864
Max Act: 5.7427. Min Act: -0.1700
Data Index: 4427703 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19