Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.9506. Min Act: -0.1700
Data Index: 4166737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.8568. Min Act: -0.1700
Data Index: 6317913 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.7631. Min Act: -0.1700
Data Index: 7011920 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.7631. Min Act: -0.1700
Data Index: 3430313 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.7006. Min Act: -0.1700
Data Index: 3025473 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.6068. Min Act: -0.1700
Data Index: 178371 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4441260 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4127912 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.6068. Min Act: -0.1700
Data Index: 2316368 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5756. Min Act: -0.1700
Data Index: 6942224 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5756. Min Act: -0.1700
Data Index: 996102 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5756. Min Act: -0.1700
Data Index: 4468437 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5443. Min Act: -0.1700
Data Index: 665019 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5443. Min Act: -0.1700
Data Index: 5977552 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5131. Min Act: -0.1700
Data Index: 5952345 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5131. Min Act: -0.1700
Data Index: 5961971 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5131. Min Act: -0.1700
Data Index: 5264146 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5131. Min Act: -0.1700
Data Index: 6656960 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5443. Min Act: -0.1700
Data Index: 6915873 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9506. Min Range: -5.9506
Max Act: 5.5131. Min Act: -0.1700
Data Index: 2184933 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19