Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1729. Min Range: -9.1729
Max Act: 9.1729. Min Act: -0.1700
Data Index: 5557308 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1729. Min Range: -9.1729
Max Act: 9.1729. Min Act: -0.1700
Data Index: 7328656 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1729. Min Range: -9.1729
Max Act: 9.1104. Min Act: -0.1700
Data Index: 1955838 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1729. Min Range: -9.1729
Max Act: 9.1104. Min Act: -0.1700
Data Index: 685564 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1729. Min Range: -9.1729
Max Act: 9.1104. Min Act: -0.1700
Data Index: 556694 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9854. Min Act: -0.1700
Data Index: 3611932 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9854. Min Act: -0.1700
Data Index: 4175630 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9854. Min Act: -0.1700
Data Index: 2415658 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9854. Min Act: -0.1700
Data Index: 5799975 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 3660983 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 7407221 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 4228040 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 852120 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 923654 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 1094660 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 2069524 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 4652928 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 6504429 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 7961796 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1729. Min Range: -9.1729
Max Act: 8.9229. Min Act: -0.1700
Data Index: 5773581 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19