Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1509 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3323879 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.2846. Min Act: -0.1700
Data Index: 2592707 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.2221. Min Act: -0.1700
Data Index: 2608438 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7773846 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.2221. Min Act: -0.1700
Data Index: 701679 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1908. Min Act: -0.1700
Data Index: 7100025 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1711169 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1908. Min Act: -0.1700
Data Index: 2749702 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1596. Min Act: -0.1700
Data Index: 3935463 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1596. Min Act: -0.1700
Data Index: 701678 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1283. Min Act: -0.1700
Data Index: 1196 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1283. Min Act: -0.1697
Data Index: 91064 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.1283. Min Act: -0.1698
Data Index: 5872673 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0971. Min Act: -0.1700
Data Index: 1625801 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 7672461 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 3724246 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0971. Min Act: -0.1700
Data Index: 5153383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 814378 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0658. Min Act: -0.1699
Data Index: 585922 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6908. Min Range: -5.6908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 6169818 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19