Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.8868. Min Act: -0.1700
Data Index: 1055450 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.8555. Min Act: -0.1700
Data Index: 2870258 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.8868. Min Act: -0.1700
Data Index: 8511160 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.8243. Min Act: -0.1700
Data Index: 5393258 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7930. Min Act: -0.1700
Data Index: 1677626 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7930. Min Act: -0.1700
Data Index: 751632 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7930. Min Act: -0.1700
Data Index: 3409868 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7930. Min Act: -0.1700
Data Index: 1670235 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7618. Min Act: -0.1700
Data Index: 578833 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7305. Min Act: -0.1700
Data Index: 6838051 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7305. Min Act: -0.1700
Data Index: 1421316 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.7305. Min Act: -0.1700
Data Index: 2605547 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6993. Min Act: -0.1700
Data Index: 5119516 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6993. Min Act: -0.1700
Data Index: 7433150 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6680. Min Act: -0.1700
Data Index: 2255005 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6680. Min Act: -0.1700
Data Index: 3122246 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6680. Min Act: -0.1700
Data Index: 6928320 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6680. Min Act: -0.1700
Data Index: 4198871 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1278357 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8868. Min Range: -5.8868
Max Act: 5.5743. Min Act: -0.1700
Data Index: 3531686 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19