Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0338. Min Range: -7.0338
Max Act: 7.0338. Min Act: -0.1700
Data Index: 7592057 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.7213. Min Act: -0.1700
Data Index: 2884784 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.5025. Min Act: -0.1700
Data Index: 250975 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.2838. Min Act: -0.1700
Data Index: 826291 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.2838. Min Act: -0.1700
Data Index: 7981990 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.1275. Min Act: -0.1700
Data Index: 5890523 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.1275. Min Act: -0.1700
Data Index: 8657673 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.0963. Min Act: -0.1700
Data Index: 822261 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4453067 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.0025. Min Act: -0.1700
Data Index: 118823 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0338. Min Range: -7.0338
Max Act: 6.0338. Min Act: -0.1700
Data Index: 2076024 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.9400. Min Act: -0.1700
Data Index: 5233388 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.9713. Min Act: -0.1700
Data Index: 667350 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.9713. Min Act: -0.1700
Data Index: 4821521 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.9400. Min Act: -0.1700
Data Index: 8374163 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.9088. Min Act: -0.1700
Data Index: 6977994 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.8775. Min Act: -0.1700
Data Index: 4963886 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.8775. Min Act: -0.1700
Data Index: 2647662 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.8775. Min Act: -0.1700
Data Index: 4118319 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0338. Min Range: -7.0338
Max Act: 5.8775. Min Act: -0.1700
Data Index: 867343 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19