Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 179 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.2715. Min Act: -0.1700
Data Index: 7884579 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5741634 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.2090. Min Act: -0.1700
Data Index: 8126680 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.2090. Min Act: -0.1700
Data Index: 7563984 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1521563 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1777. Min Act: -0.1700
Data Index: 3977848 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1777. Min Act: -0.1700
Data Index: 719059 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1777. Min Act: -0.1700
Data Index: 4903643 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1152. Min Act: -0.1700
Data Index: 4383975 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1465. Min Act: -0.1700
Data Index: 919303 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1777. Min Act: -0.1700
Data Index: 4488761 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1465. Min Act: -0.1700
Data Index: 964440 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1152. Min Act: -0.1700
Data Index: 888347 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.1152. Min Act: -0.1700
Data Index: 4447515 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0840. Min Act: -0.1700
Data Index: 8224994 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4754591 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0527. Min Act: -0.1700
Data Index: 244202 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0215. Min Act: -0.1700
Data Index: 4921191 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0215. Min Act: -0.1700
Data Index: 7088838 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2715. Min Range: -5.2715
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4357774 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19