Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0561. Min Range: -7.0561
Max Act: 7.0561. Min Act: -0.1700
Data Index: 1939661 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.9936. Min Act: -0.1700
Data Index: 3461488 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.9623. Min Act: -0.1700
Data Index: 8436726 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.9623. Min Act: -0.1700
Data Index: 6052456 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.9623. Min Act: -0.1700
Data Index: 5211814 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.9311. Min Act: -0.1700
Data Index: 7939484 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8373. Min Act: -0.1700
Data Index: 3983804 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8686. Min Act: -0.1700
Data Index: 621301 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8373. Min Act: -0.1700
Data Index: 3834855 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8373. Min Act: -0.1700
Data Index: 1999133 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8061. Min Act: -0.1700
Data Index: 2367746 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8061. Min Act: -0.1700
Data Index: 584027 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8061. Min Act: -0.1700
Data Index: 1939642 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7748. Min Act: -0.1700
Data Index: 8555465 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7748. Min Act: -0.1700
Data Index: 5752028 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7748. Min Act: -0.1700
Data Index: 6056030 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7748. Min Act: -0.1700
Data Index: 1022530 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7436. Min Act: -0.1700
Data Index: 2321770 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7436. Min Act: -0.1700
Data Index: 2356083 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.7123. Min Act: -0.1700
Data Index: 2158705 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19