Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.6723. Min Act: -0.1700
Data Index: 2358283 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.6410. Min Act: -0.1700
Data Index: 5897837 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.5785. Min Act: -0.1700
Data Index: 1165875 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.4223. Min Act: -0.1700
Data Index: 8492179 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.4535. Min Act: -0.1700
Data Index: 4348679 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.4223. Min Act: -0.1700
Data Index: 5265197 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.3598. Min Act: -0.1700
Data Index: 6336162 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.2660. Min Act: -0.1700
Data Index: 2825444 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.2035. Min Act: -0.1700
Data Index: 8016155 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 7087458 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 1906733 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 76721 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 2061474 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 3252287 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4426767 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.1098. Min Act: -0.1700
Data Index: 5546078 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.0785. Min Act: -0.1700
Data Index: 6014826 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.0785. Min Act: -0.1700
Data Index: 2264506 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.0785. Min Act: -0.1700
Data Index: 3059857 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6723. Min Range: -6.6723
Max Act: 6.0473. Min Act: -0.1700
Data Index: 6059090 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19