Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 911 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.5047. Min Act: -0.1700
Data Index: 1945353 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.4422. Min Act: -0.1700
Data Index: 4361163 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.3485. Min Act: -0.1700
Data Index: 4600340 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.3172. Min Act: -0.1700
Data Index: 1735300 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.3172. Min Act: -0.1700
Data Index: 8275582 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.2235. Min Act: -0.1700
Data Index: 1998626 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.2235. Min Act: -0.1700
Data Index: 2024956 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.2235. Min Act: -0.1700
Data Index: 7571651 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.1297. Min Act: -0.1700
Data Index: 2365893 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0985. Min Act: -0.1700
Data Index: 3552041 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0672. Min Act: -0.1700
Data Index: 8343967 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0672. Min Act: -0.1700
Data Index: 2214136 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0672. Min Act: -0.1700
Data Index: 7046073 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0672. Min Act: -0.1700
Data Index: 7424353 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5762079 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0360. Min Act: -0.1700
Data Index: 8321034 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0360. Min Act: -0.1700
Data Index: 1796012 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0360. Min Act: -0.1700
Data Index: 8460054 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0047. Min Act: -0.1700
Data Index: 330768 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5047. Min Range: -6.5047
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5762078 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19