Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.5723. Min Act: -0.1700
Data Index: 728047 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.4785. Min Act: -0.1700
Data Index: 7186644 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.4160. Min Act: -0.1700
Data Index: 2342345 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.3535. Min Act: -0.1700
Data Index: 1742000 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.3223. Min Act: -0.1700
Data Index: 5785460 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.3223. Min Act: -0.1700
Data Index: 5688715 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.2598. Min Act: -0.1700
Data Index: 6669780 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.2598. Min Act: -0.1700
Data Index: 1991009 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.2598. Min Act: -0.1700
Data Index: 1119235 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1660. Min Act: -0.1700
Data Index: 2417697 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1660. Min Act: -0.1700
Data Index: 4539025 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1660. Min Act: -0.1700
Data Index: 6588782 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1035. Min Act: -0.1700
Data Index: 1991029 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1035. Min Act: -0.1700
Data Index: 7897529 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1348. Min Act: -0.1700
Data Index: 708401 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1035. Min Act: -0.1700
Data Index: 2136329 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1035. Min Act: -0.1700
Data Index: 5649050 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.1035. Min Act: -0.1700
Data Index: 1882634 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.0723. Min Act: -0.1700
Data Index: 6040420 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5723. Min Range: -4.5723
Max Act: 4.0723. Min Act: -0.1700
Data Index: 6474677 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19