Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 531 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.5083. Min Act: -0.1700
Data Index: 8316855 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.4458. Min Act: -0.1700
Data Index: 3482566 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.3208. Min Act: -0.1700
Data Index: 6030122 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.2583. Min Act: -0.1700
Data Index: 7348779 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.2583. Min Act: -0.1700
Data Index: 131140 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.2270. Min Act: -0.1700
Data Index: 8665614 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.2270. Min Act: -0.1700
Data Index: 2867568 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1645. Min Act: -0.1700
Data Index: 7301731 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1645. Min Act: -0.1700
Data Index: 6303166 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1333. Min Act: -0.1700
Data Index: 6300843 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1333. Min Act: -0.1700
Data Index: 4887817 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3533319 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1333. Min Act: -0.1700
Data Index: 599189 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1020. Min Act: -0.1700
Data Index: 141754 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.1020. Min Act: -0.1700
Data Index: 8397987 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.0395. Min Act: -0.1700
Data Index: 6751295 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.0083. Min Act: -0.1700
Data Index: 1465067 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5083. Min Range: -6.5083
Max Act: 6.0083. Min Act: -0.1700
Data Index: 414059 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5083. Min Range: -6.5083
Max Act: 5.9770. Min Act: -0.1700
Data Index: 6615611 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5083. Min Range: -6.5083
Max Act: 5.9770. Min Act: -0.1700
Data Index: 2927308 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19