Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.7450. Min Act: -0.1700
Data Index: 4111808 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.6825. Min Act: -0.1700
Data Index: 2070504 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.6512. Min Act: -0.1700
Data Index: 2058561 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.6200. Min Act: -0.1700
Data Index: 5853890 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.6200. Min Act: -0.1700
Data Index: 3548177 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.6200. Min Act: -0.1700
Data Index: 4141131 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5887. Min Act: -0.1700
Data Index: 8223164 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5575. Min Act: -0.1700
Data Index: 2179536 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5575. Min Act: -0.1700
Data Index: 6621749 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5262. Min Act: -0.1700
Data Index: 7755205 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5262. Min Act: -0.1700
Data Index: 3475623 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4950. Min Act: -0.1700
Data Index: 7073967 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4637. Min Act: -0.1700
Data Index: 2488779 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4325. Min Act: -0.1700
Data Index: 8101030 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4325. Min Act: -0.1700
Data Index: 1733079 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4012. Min Act: -0.1700
Data Index: 328804 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.3700. Min Act: -0.1700
Data Index: 5892104 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.3700. Min Act: -0.1700
Data Index: 4441579 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.3700. Min Act: -0.1700
Data Index: 457628 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.3387. Min Act: -0.1700
Data Index: 4531259 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19