Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.5741. Min Act: -0.1700
Data Index: 3935636 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.3866. Min Act: -0.1700
Data Index: 4602020 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.2616. Min Act: -0.1700
Data Index: 7328013 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.2303. Min Act: -0.1700
Data Index: 1412690 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.0741. Min Act: -0.1700
Data Index: 3098393 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5741. Min Range: -7.5741
Max Act: 7.0428. Min Act: -0.1700
Data Index: 688923 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.9803. Min Act: -0.1700
Data Index: 8298403 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.9178. Min Act: -0.1700
Data Index: 7103325 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.9178. Min Act: -0.1700
Data Index: 858994 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.9178. Min Act: -0.1700
Data Index: 6077599 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8866. Min Act: -0.1700
Data Index: 4039372 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 4539961 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 5964008 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8866. Min Act: -0.1700
Data Index: 7207330 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 1551253 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 1820657 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 6335651 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8553. Min Act: -0.1700
Data Index: 4732890 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8241. Min Act: -0.1700
Data Index: 3289049 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5741. Min Range: -7.5741
Max Act: 6.8241. Min Act: -0.1700
Data Index: 5682359 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19