Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0664. Min Act: -0.1700
Data Index: 4628230 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0348. Min Act: -0.1700
Data Index: 4779236 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0348. Min Act: -0.1700
Data Index: 5568369 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0190. Min Act: -0.1700
Data Index: 4779229 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0190. Min Act: -0.1700
Data Index: 2384909 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0664. Min Range: -3.0664
Max Act: 3.0033. Min Act: -0.1700
Data Index: 879689 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9874. Min Act: -0.1700
Data Index: 2761792 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9558. Min Act: -0.1700
Data Index: 7641887 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9558. Min Act: -0.1700
Data Index: 2239769 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 164094 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 7988970 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9558. Min Act: -0.1700
Data Index: 4779227 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 2210177 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 7411718 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 5220952 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9400. Min Act: -0.1700
Data Index: 1323344 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9241. Min Act: -0.1700
Data Index: 7142232 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1985288 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.8924. Min Act: -0.1700
Data Index: 4330266 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0664. Min Range: -3.0664
Max Act: 2.8924. Min Act: -0.1700
Data Index: 7145091 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19