Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5417 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.7460. Min Act: -0.1700
Data Index: 1691568 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6522. Min Act: -0.1700
Data Index: 5458727 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 4400792 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5536443 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5272. Min Act: -0.1700
Data Index: 6354514 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4647. Min Act: -0.1700
Data Index: 1581981 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4960. Min Act: -0.1700
Data Index: 7097257 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4960. Min Act: -0.1700
Data Index: 3242989 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4647. Min Act: -0.1700
Data Index: 1085165 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4335. Min Act: -0.1700
Data Index: 7268672 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4335. Min Act: -0.1700
Data Index: 272259 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4335. Min Act: -0.1700
Data Index: 6087312 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5103595 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4022. Min Act: -0.1700
Data Index: 282734 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4022. Min Act: -0.1700
Data Index: 8141196 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4022. Min Act: -0.1700
Data Index: 7744529 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3974512 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3159391 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.3710. Min Act: -0.1700
Data Index: 1167638 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.3397. Min Act: -0.1700
Data Index: 1010549 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19