Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7811. Min Act: -0.1700
Data Index: 795490 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7811. Min Act: -0.1700
Data Index: 5429602 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7498. Min Act: -0.1700
Data Index: 6236973 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7498. Min Act: -0.1700
Data Index: 217089 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 2547386 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 8044250 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6873. Min Act: -0.1700
Data Index: 7006823 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 4026803 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 6764328 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6873. Min Act: -0.1700
Data Index: 1324674 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 8647474 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 8636671 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6873. Min Act: -0.1700
Data Index: 8700777 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 379237 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.7186. Min Act: -0.1700
Data Index: 3398847 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6873. Min Act: -0.1700
Data Index: 3398848 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6873. Min Act: -0.1700
Data Index: 5337179 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6248. Min Act: -0.1700
Data Index: 4242334 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6561. Min Act: -0.1700
Data Index: 4413285 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7811. Min Range: -6.7811
Max Act: 6.6561. Min Act: -0.1700
Data Index: 529188 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19