Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.8724. Min Act: -0.1700
Data Index: 8403281 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.8099. Min Act: -0.1700
Data Index: 5935405 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.8099. Min Act: -0.1700
Data Index: 6350222 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.8099. Min Act: -0.1700
Data Index: 7068734 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.7630. Min Act: -0.1700
Data Index: 4497527 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.7317. Min Act: -0.1700
Data Index: 440738 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.7160. Min Act: -0.1700
Data Index: 407077 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.7004. Min Act: -0.1700
Data Index: 5254862 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.7004. Min Act: -0.1700
Data Index: 1779708 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6848. Min Act: -0.1700
Data Index: 4497528 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6848. Min Act: -0.1700
Data Index: 2865916 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6535. Min Act: -0.1700
Data Index: 8708472 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6691. Min Act: -0.1700
Data Index: 500472 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6691. Min Act: -0.1700
Data Index: 2466780 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6535. Min Act: -0.1700
Data Index: 2221509 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6535. Min Act: -0.1700
Data Index: 5790223 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6691. Min Act: -0.1700
Data Index: 7974956 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6378. Min Act: -0.1700
Data Index: 5476625 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6065. Min Act: -0.1700
Data Index: 1484414 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8724. Min Range: -3.8724
Max Act: 3.6222. Min Act: -0.1700
Data Index: 3015779 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19