Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 5179615 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 4364617 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 4034673 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 724302 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8532. Min Act: -0.1700
Data Index: 521173 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8219. Min Act: -0.1700
Data Index: 6185576 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8219. Min Act: -0.1700
Data Index: 5426811 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6969. Min Act: -0.1700
Data Index: 231904 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6969. Min Act: -0.1700
Data Index: 3973218 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6969. Min Act: -0.1700
Data Index: 1498399 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 1160492 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6022291 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6603740 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7578624 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 962312 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 3798577 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 7073161 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 5908127 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 6715670 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 2682044 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19