Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.7322. Min Act: -0.1700
Data Index: 6543302 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.4510. Min Act: -0.1700
Data Index: 5905090 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.3572. Min Act: -0.1700
Data Index: 8454793 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.3572. Min Act: -0.1700
Data Index: 3584402 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.2635. Min Act: -0.1700
Data Index: 500299 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.2322. Min Act: -0.1700
Data Index: 3555586 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.2322. Min Act: -0.1700
Data Index: 1568756 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.2635. Min Act: -0.1700
Data Index: 4287083 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.1697. Min Act: -0.1700
Data Index: 3201671 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.2010. Min Act: -0.1700
Data Index: 8091619 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.1697. Min Act: -0.1700
Data Index: 6701903 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.1697. Min Act: -0.1700
Data Index: 8796007 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.1697. Min Act: -0.1700
Data Index: 1863700 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.1385. Min Act: -0.1700
Data Index: 6004225 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0135. Min Act: -0.1700
Data Index: 3745120 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0447. Min Act: -0.1700
Data Index: 7278155 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0447. Min Act: -0.1700
Data Index: 6102398 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0760. Min Act: -0.1700
Data Index: 5431886 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0135. Min Act: -0.1700
Data Index: 7648733 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7322. Min Range: -6.7322
Max Act: 6.0135. Min Act: -0.1700
Data Index: 8302934 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19