Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1588. Min Range: -6.1588
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2366346 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1588. Min Range: -6.1588
Max Act: 6.0963. Min Act: -0.1700
Data Index: 1322346 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.9088. Min Act: -0.1700
Data Index: 3496358 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.8775. Min Act: -0.1700
Data Index: 4840576 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.8775. Min Act: -0.1700
Data Index: 636571 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.7838. Min Act: -0.1700
Data Index: 3284062 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8683632 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6900. Min Act: -0.1700
Data Index: 277860 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6900. Min Act: -0.1700
Data Index: 1895433 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6588. Min Act: -0.1700
Data Index: 4796192 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 6522894 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 5390148 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 2951906 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 2767046 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 333688 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 4330831 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7427499 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.5963. Min Act: -0.1700
Data Index: 7453623 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.5963. Min Act: -0.1700
Data Index: 7085070 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1588. Min Range: -6.1588
Max Act: 5.5963. Min Act: -0.1700
Data Index: 1931133 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19