Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.3929. Min Act: -0.1700
Data Index: 7279713 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.3304. Min Act: -0.1700
Data Index: 3270993 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2367. Min Act: -0.1700
Data Index: 1154978 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2367. Min Act: -0.1700
Data Index: 1387919 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2054. Min Act: -0.1700
Data Index: 6366756 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.1742. Min Act: -0.1700
Data Index: 6482631 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.1742. Min Act: -0.1700
Data Index: 3579226 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0804. Min Act: -0.1700
Data Index: 6421145 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0804. Min Act: -0.1700
Data Index: 895935 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0492. Min Act: -0.1700
Data Index: 8692966 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0492. Min Act: -0.1700
Data Index: 6421150 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0492. Min Act: -0.1700
Data Index: 1301685 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0492. Min Act: -0.1700
Data Index: 4876120 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0179. Min Act: -0.1700
Data Index: 2732131 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9867. Min Act: -0.1700
Data Index: 2216688 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0179. Min Act: -0.1700
Data Index: 1347267 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0179. Min Act: -0.1700
Data Index: 6421158 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9867. Min Act: -0.1700
Data Index: 6421136 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9554. Min Act: -0.1700
Data Index: 7572042 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9867. Min Act: -0.1700
Data Index: 3584464 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19