Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 3985083 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.6829. Min Act: -0.1700
Data Index: 551142 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6186519 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.5267. Min Act: -0.1700
Data Index: 475784 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.5267. Min Act: -0.1700
Data Index: 6144291 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.4954. Min Act: -0.1700
Data Index: 2014062 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.4017. Min Act: -0.1700
Data Index: 8016500 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.3704. Min Act: -0.1700
Data Index: 5462972 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.3704. Min Act: -0.1700
Data Index: 7947441 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.3392. Min Act: -0.1700
Data Index: 5988915 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.3079. Min Act: -0.1700
Data Index: 5642634 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.3079. Min Act: -0.1700
Data Index: 6659972 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.2767. Min Act: -0.1700
Data Index: 822206 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.2454. Min Act: -0.1700
Data Index: 439503 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.1829. Min Act: -0.1700
Data Index: 1101586 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.2142. Min Act: -0.1700
Data Index: 3611628 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.2142. Min Act: -0.1700
Data Index: 67348 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.2142. Min Act: -0.1700
Data Index: 6731997 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.1517. Min Act: -0.1700
Data Index: 7704994 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8079. Min Range: -5.8079
Max Act: 5.1517. Min Act: -0.1700
Data Index: 4238381 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19