Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3597. Min Range: -8.3597
Max Act: 8.3597. Min Act: -0.1700
Data Index: 2359801 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3597. Min Range: -8.3597
Max Act: 8.1097. Min Act: -0.1700
Data Index: 2211803 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3597. Min Range: -8.3597
Max Act: 8.0472. Min Act: -0.1700
Data Index: 4480158 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3597. Min Range: -8.3597
Max Act: 8.0472. Min Act: -0.1700
Data Index: 1665650 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.9847. Min Act: -0.1700
Data Index: 8811480 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.9222. Min Act: -0.1700
Data Index: 8811479 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.9847. Min Act: -0.1700
Data Index: 4238038 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.9222. Min Act: -0.1700
Data Index: 7145562 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.8597. Min Act: -0.1700
Data Index: 3042896 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.8597. Min Act: -0.1700
Data Index: 5067230 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.8597. Min Act: -0.1700
Data Index: 4179559 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7972. Min Act: -0.1700
Data Index: 8453666 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7972. Min Act: -0.1700
Data Index: 1424624 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7972. Min Act: -0.1700
Data Index: 4421137 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.8597. Min Act: -0.1700
Data Index: 7161388 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7347. Min Act: -0.1700
Data Index: 2307652 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7347. Min Act: -0.1700
Data Index: 7430204 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7347. Min Act: -0.1700
Data Index: 5281415 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7347. Min Act: -0.1700
Data Index: 7143395 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3597. Min Range: -8.3597
Max Act: 7.7347. Min Act: -0.1700
Data Index: 1752402 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19