Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.5998. Min Act: -0.1700
Data Index: 5538104 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.4436. Min Act: -0.1700
Data Index: 4985170 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.3186. Min Act: -0.1700
Data Index: 2637513 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.2561. Min Act: -0.1700
Data Index: 6534583 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.2561. Min Act: -0.1700
Data Index: 4378343 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.1311. Min Act: -0.1700
Data Index: 7201563 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0998. Min Act: -0.1700
Data Index: 7017509 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0998. Min Act: -0.1700
Data Index: 7865210 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 561385 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 140341 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0061. Min Act: -0.1700
Data Index: 5476968 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0061. Min Act: -0.1700
Data Index: 2752638 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 4111650 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0061. Min Act: -0.1700
Data Index: 2461569 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9748. Min Act: -0.1700
Data Index: 7295277 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9748. Min Act: -0.1700
Data Index: 3100155 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9436. Min Act: -0.1700
Data Index: 5558861 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9436. Min Act: -0.1700
Data Index: 1032982 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9748. Min Act: -0.1700
Data Index: 4430058 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5998. Min Range: -6.5998
Max Act: 5.9748. Min Act: -0.1700
Data Index: 4430588 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19