Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0292. Min Range: -9.0292
Max Act: 9.0292. Min Act: -0.1700
Data Index: 3676062 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.8417. Min Act: -0.1700
Data Index: 5680633 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.8417. Min Act: -0.1700
Data Index: 1408711 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.6542. Min Act: -0.1700
Data Index: 637863 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.6542. Min Act: -0.1700
Data Index: 6728285 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.5917. Min Act: -0.1700
Data Index: 820352 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.5292. Min Act: -0.1700
Data Index: 8726387 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.5292. Min Act: -0.1700
Data Index: 8339493 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.5292. Min Act: -0.1700
Data Index: 2284055 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.5292. Min Act: -0.1700
Data Index: 6808498 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.4667. Min Act: -0.1700
Data Index: 8211065 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.4667. Min Act: -0.1700
Data Index: 1713042 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.4042. Min Act: -0.1700
Data Index: 6932220 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.3417. Min Act: -0.1700
Data Index: 7062289 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.4042. Min Act: -0.1700
Data Index: 8713598 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.3417. Min Act: -0.1700
Data Index: 5360469 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.3417. Min Act: -0.1700
Data Index: 4185136 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.2792. Min Act: -0.1700
Data Index: 3196003 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.2167. Min Act: -0.1700
Data Index: 8669902 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0292. Min Range: -9.0292
Max Act: 8.2792. Min Act: -0.1700
Data Index: 6063552 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19