Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5225 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.6218. Min Act: -0.1700
Data Index: 7136065 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5905. Min Act: -0.1700
Data Index: 2113057 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5905. Min Act: -0.1700
Data Index: 6114931 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5593. Min Act: -0.1700
Data Index: 6539971 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5905. Min Act: -0.1700
Data Index: 5667449 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5280. Min Act: -0.1700
Data Index: 2183854 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.5280. Min Act: -0.1700
Data Index: 303369 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4968. Min Act: -0.1700
Data Index: 2516353 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4655. Min Act: -0.1700
Data Index: 6356449 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4343. Min Act: -0.1700
Data Index: 3161820 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4343. Min Act: -0.1700
Data Index: 5554205 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4030. Min Act: -0.1700
Data Index: 909165 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4030. Min Act: -0.1700
Data Index: 6687141 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.4030. Min Act: -0.1700
Data Index: 7136062 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3718. Min Act: -0.1700
Data Index: 6605739 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3718. Min Act: -0.1700
Data Index: 3066406 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3718. Min Act: -0.1700
Data Index: 5363141 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3405. Min Act: -0.1700
Data Index: 6010843 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3405. Min Act: -0.1700
Data Index: 6379702 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6218. Min Range: -6.6218
Max Act: 6.3405. Min Act: -0.1700
Data Index: 1134181 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19