Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.9848. Min Act: -0.1700
Data Index: 8164719 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.9223. Min Act: -0.1700
Data Index: 8310995 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.7660. Min Act: -0.1700
Data Index: 6914535 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.6723. Min Act: -0.1700
Data Index: 7797042 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.6723. Min Act: -0.1700
Data Index: 6579410 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.6723. Min Act: -0.1700
Data Index: 2749818 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.5785. Min Act: -0.1700
Data Index: 1671783 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.5785. Min Act: -0.1700
Data Index: 1921812 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.5473. Min Act: -0.1700
Data Index: 690581 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.4848. Min Act: -0.1700
Data Index: 8358609 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.4848. Min Act: -0.1700
Data Index: 8720154 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.4848. Min Act: -0.1700
Data Index: 6148458 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.3285. Min Act: -0.1700
Data Index: 3733821 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.3598. Min Act: -0.1700
Data Index: 4341489 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.3285. Min Act: -0.1700
Data Index: 4015123 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.2973. Min Act: -0.1700
Data Index: 8182204 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.2660. Min Act: -0.1700
Data Index: 4849886 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.2660. Min Act: -0.1700
Data Index: 1891120 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.2660. Min Act: -0.1700
Data Index: 5886979 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9848. Min Range: -6.9848
Max Act: 6.2660. Min Act: -0.1700
Data Index: 5208464 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19