Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5644 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0767. Min Range: -5.0767
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5791141 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.9517. Min Act: -0.1700
Data Index: 202807 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.8892. Min Act: -0.1700
Data Index: 7110211 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.9205. Min Act: -0.1700
Data Index: 3276393 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.8267. Min Act: -0.1700
Data Index: 6682976 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.8267. Min Act: -0.1700
Data Index: 1904378 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7955. Min Act: -0.1700
Data Index: 4802341 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7955. Min Act: -0.1700
Data Index: 6827470 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7330. Min Act: -0.1700
Data Index: 3292875 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7330. Min Act: -0.1700
Data Index: 2664215 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7642. Min Act: -0.1700
Data Index: 1880485 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7642. Min Act: -0.1700
Data Index: 304904 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7017. Min Act: -0.1700
Data Index: 4119768 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7017. Min Act: -0.1700
Data Index: 5134655 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.6705. Min Act: -0.1700
Data Index: 5027048 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.6705. Min Act: -0.1700
Data Index: 8733076 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7017. Min Act: -0.1700
Data Index: 8340927 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.6705. Min Act: -0.1700
Data Index: 2365742 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.7017. Min Act: -0.1700
Data Index: 8812161 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0767. Min Range: -5.0767
Max Act: 4.6392. Min Act: -0.1700
Data Index: 6360570 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19