Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1892. Min Act: -0.1700
Data Index: 3417530 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.2205. Min Act: -0.1700
Data Index: 309143 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1580. Min Act: -0.1700
Data Index: 7552179 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1892. Min Act: -0.1700
Data Index: 2388475 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0955. Min Act: -0.1700
Data Index: 6339151 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0642. Min Act: -0.1700
Data Index: 8088478 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0642. Min Act: -0.1700
Data Index: 4996660 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 3752864 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 5261916 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 5673061 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0017. Min Act: -0.1700
Data Index: 2202469 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 202174 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0017. Min Act: -0.1700
Data Index: 1967359 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0017. Min Act: -0.1700
Data Index: 7938819 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 6854400 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0017. Min Act: -0.1700
Data Index: 3841954 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0017. Min Act: -0.1700
Data Index: 6618654 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9705. Min Act: -0.1700
Data Index: 4003198 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9705. Min Act: -0.1700
Data Index: 3415554 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9392. Min Act: -0.1700
Data Index: 4091011 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19