Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.6771. Min Act: -0.1700
Data Index: 4700768 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.5834. Min Act: -0.1700
Data Index: 8304567 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.4584. Min Act: -0.1700
Data Index: 1982598 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.3646. Min Act: -0.1700
Data Index: 904879 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.3334. Min Act: -0.1700
Data Index: 4304714 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.3021. Min Act: -0.1700
Data Index: 4020538 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.2709. Min Act: -0.1700
Data Index: 1071780 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.2709. Min Act: -0.1700
Data Index: 8618895 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.2709. Min Act: -0.1700
Data Index: 959967 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.1771. Min Act: -0.1700
Data Index: 6011276 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.1459. Min Act: -0.1700
Data Index: 5099274 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6387592 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0834. Min Act: -0.1700
Data Index: 2626360 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2672703 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0521. Min Act: -0.1700
Data Index: 7946148 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0521. Min Act: -0.1700
Data Index: 8645741 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0521. Min Act: -0.1700
Data Index: 3359595 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0209. Min Act: -0.1700
Data Index: 3861124 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6387593 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6771. Min Range: -6.6771
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6031907 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19