Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 158 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1935. Min Range: -8.1935
Max Act: 8.1935. Min Act: -0.1700
Data Index: 3371403 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.8810. Min Act: -0.1700
Data Index: 168767 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.5685. Min Act: -0.1700
Data Index: 812636 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.5685. Min Act: -0.1700
Data Index: 5232565 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.4748. Min Act: -0.1700
Data Index: 7205894 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.3810. Min Act: -0.1700
Data Index: 1754386 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.3185. Min Act: -0.1700
Data Index: 4493468 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.3185. Min Act: -0.1700
Data Index: 3944954 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.3185. Min Act: -0.1700
Data Index: 5876990 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.3185. Min Act: -0.1700
Data Index: 1340675 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.2873. Min Act: -0.1700
Data Index: 7023018 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.1935. Min Act: -0.1700
Data Index: 1745920 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.1935. Min Act: -0.1700
Data Index: 5746503 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.1310. Min Act: -0.1700
Data Index: 6627636 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.1310. Min Act: -0.1700
Data Index: 6027231 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.0998. Min Act: -0.1700
Data Index: 6407320 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.0998. Min Act: -0.1700
Data Index: 2531059 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.1310. Min Act: -0.1700
Data Index: 951559 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.0998. Min Act: -0.1700
Data Index: 925034 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1935. Min Range: -8.1935
Max Act: 7.0998. Min Act: -0.1700
Data Index: 7028372 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19