Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.8702. Min Act: -0.1700
Data Index: 6832918 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.7452. Min Act: -0.1700
Data Index: 1338632 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.6827. Min Act: -0.1700
Data Index: 4873776 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6170191 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.5890. Min Act: -0.1700
Data Index: 2368974 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.5890. Min Act: -0.1700
Data Index: 3689441 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.5890. Min Act: -0.1700
Data Index: 6585243 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.5577. Min Act: -0.1700
Data Index: 6982775 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4952. Min Act: -0.1700
Data Index: 2368973 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4952. Min Act: -0.1700
Data Index: 5145822 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4327. Min Act: -0.1700
Data Index: 8321187 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4327. Min Act: -0.1700
Data Index: 4949188 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4327. Min Act: -0.1700
Data Index: 8565496 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4015. Min Act: -0.1700
Data Index: 8707966 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.4015. Min Act: -0.1700
Data Index: 2506510 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.3702. Min Act: -0.1700
Data Index: 5509674 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.3390. Min Act: -0.1700
Data Index: 8399284 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.3390. Min Act: -0.1700
Data Index: 5145827 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.3390. Min Act: -0.1700
Data Index: 6050769 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8702. Min Range: -5.8702
Max Act: 5.3390. Min Act: -0.1700
Data Index: 4281486 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19