Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.4390. Min Act: -0.1700
Data Index: 744832 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.4077. Min Act: -0.1700
Data Index: 5638332 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.2827. Min Act: -0.1700
Data Index: 3162423 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.2515. Min Act: -0.1700
Data Index: 1110346 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.2515. Min Act: -0.1700
Data Index: 7046927 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.2515. Min Act: -0.1700
Data Index: 7443072 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.2202. Min Act: -0.1700
Data Index: 4313042 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.1890. Min Act: -0.1700
Data Index: 5313016 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5550924 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3091176 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3908953 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2056918 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6071019 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0952. Min Act: -0.1700
Data Index: 808672 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0640. Min Act: -0.1700
Data Index: 3579922 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0640. Min Act: -0.1700
Data Index: 8036762 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0640. Min Act: -0.1700
Data Index: 4092262 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4466261 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0640. Min Act: -0.1700
Data Index: 4256608 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4390. Min Range: -5.4390
Max Act: 5.0327. Min Act: -0.1700
Data Index: 210235 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19