Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3723. Min Range: -7.3723
Max Act: 7.3723. Min Act: -0.1700
Data Index: 3883801 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3723. Min Range: -7.3723
Max Act: 7.2786. Min Act: -0.1700
Data Index: 6847520 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3723. Min Range: -7.3723
Max Act: 7.1536. Min Act: -0.1700
Data Index: 824286 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.8723. Min Act: -0.1700
Data Index: 8580609 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.8098. Min Act: -0.1700
Data Index: 7840657 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.7786. Min Act: -0.1700
Data Index: 7776383 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.5911. Min Act: -0.1700
Data Index: 3314258 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.5598. Min Act: -0.1700
Data Index: 5105819 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.4973. Min Act: -0.1700
Data Index: 3441054 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 5308161 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 3168249 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 779945 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3411. Min Act: -0.1700
Data Index: 4394041 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 86509 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3098. Min Act: -0.1700
Data Index: 5826724 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 361411 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.2786. Min Act: -0.1700
Data Index: 8823075 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.2786. Min Act: -0.1700
Data Index: 6153125 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.2786. Min Act: -0.1700
Data Index: 6476743 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3723. Min Range: -7.3723
Max Act: 6.2473. Min Act: -0.1700
Data Index: 3856923 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19