Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2840. Min Range: -9.2840
Max Act: 9.2840. Min Act: -0.1700
Data Index: 147185 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2840. Min Range: -9.2840
Max Act: 9.1590. Min Act: -0.1700
Data Index: 4658140 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.9090. Min Act: -0.1700
Data Index: 732629 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.9090. Min Act: -0.1700
Data Index: 767602 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.8465. Min Act: -0.1700
Data Index: 3855436 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.7215. Min Act: -0.1700
Data Index: 2632816 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.7215. Min Act: -0.1700
Data Index: 6551083 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.6590. Min Act: -0.1700
Data Index: 1269048 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.6590. Min Act: -0.1700
Data Index: 2855093 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.6590. Min Act: -0.1700
Data Index: 2209602 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.5965. Min Act: -0.1700
Data Index: 6699840 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.5965. Min Act: -0.1700
Data Index: 8621791 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.5965. Min Act: -0.1700
Data Index: 6796526 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.5340. Min Act: -0.1700
Data Index: 459561 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.4715. Min Act: -0.1700
Data Index: 1016135 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.5340. Min Act: -0.1700
Data Index: 1351991 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.4715. Min Act: -0.1700
Data Index: 2931686 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.4715. Min Act: -0.1700
Data Index: 6661354 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.3465. Min Act: -0.1700
Data Index: 3454858 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2840. Min Range: -9.2840
Max Act: 8.4090. Min Act: -0.1700
Data Index: 882586 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19