Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2341. Min Range: -6.2341
Max Act: 6.2341. Min Act: -0.1700
Data Index: 5702340 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2341. Min Range: -6.2341
Max Act: 6.2028. Min Act: -0.1700
Data Index: 4076911 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2341. Min Range: -6.2341
Max Act: 6.0466. Min Act: -0.1700
Data Index: 186901 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2341. Min Range: -6.2341
Max Act: 6.0153. Min Act: -0.1700
Data Index: 340227 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9841. Min Act: -0.1700
Data Index: 2287713 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9841. Min Act: -0.1700
Data Index: 1167402 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9528. Min Act: -0.1700
Data Index: 1548647 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9528. Min Act: -0.1700
Data Index: 7942686 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9216. Min Act: -0.1700
Data Index: 2133735 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9216. Min Act: -0.1700
Data Index: 7471292 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9528. Min Act: -0.1700
Data Index: 264265 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8903. Min Act: -0.1700
Data Index: 5881787 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8903. Min Act: -0.1700
Data Index: 6474857 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.9216. Min Act: -0.1700
Data Index: 2948920 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8278. Min Act: -0.1700
Data Index: 4377742 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8591. Min Act: -0.1700
Data Index: 3397702 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8591. Min Act: -0.1700
Data Index: 6160748 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8903. Min Act: -0.1700
Data Index: 147560 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8278. Min Act: -0.1700
Data Index: 1381359 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2341. Min Range: -6.2341
Max Act: 5.8278. Min Act: -0.1700
Data Index: 5517838 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19