Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.5996. Min Act: -0.1700
Data Index: 7626576 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.4746. Min Act: -0.1700
Data Index: 2894685 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.4121. Min Act: -0.1700
Data Index: 982552 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.2871. Min Act: -0.1700
Data Index: 4556380 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.1621. Min Act: -0.1700
Data Index: 2962058 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.0996. Min Act: -0.1700
Data Index: 4289890 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.0996. Min Act: -0.1700
Data Index: 8015408 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5996. Min Range: -8.5996
Max Act: 8.0996. Min Act: -0.1700
Data Index: 7901952 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.9746. Min Act: -0.1700
Data Index: 4948937 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.9746. Min Act: -0.1700
Data Index: 999226 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.9121. Min Act: -0.1700
Data Index: 4909027 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.8496. Min Act: -0.1700
Data Index: 1180878 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.7871. Min Act: -0.1700
Data Index: 5735737 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.7246. Min Act: -0.1700
Data Index: 1364260 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6933. Min Act: -0.1700
Data Index: 2806972 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6933. Min Act: -0.1700
Data Index: 2366755 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6933. Min Act: -0.1700
Data Index: 2993119 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6621. Min Act: -0.1700
Data Index: 2963953 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6308. Min Act: -0.1700
Data Index: 19634 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5996. Min Range: -8.5996
Max Act: 7.6621. Min Act: -0.1700
Data Index: 6988134 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19