Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3132 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.4024. Min Act: -0.1700
Data Index: 536793 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.3087. Min Act: -0.1700
Data Index: 4683290 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.3399. Min Act: -0.1700
Data Index: 1638163 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.2774. Min Act: -0.1700
Data Index: 2167472 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.2462. Min Act: -0.1700
Data Index: 4970073 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2199848 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2258854 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.2149. Min Act: -0.1700
Data Index: 4796465 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1837. Min Act: -0.1700
Data Index: 440857 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1837. Min Act: -0.1700
Data Index: 5606831 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1524. Min Act: -0.1700
Data Index: 5154896 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1524. Min Act: -0.1700
Data Index: 2673940 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1524. Min Act: -0.1700
Data Index: 810036 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1212. Min Act: -0.1700
Data Index: 177313 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.0899. Min Act: -0.1700
Data Index: 1370752 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.0899. Min Act: -0.1700
Data Index: 5455331 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.0899. Min Act: -0.1700
Data Index: 4209717 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.0899. Min Act: -0.1700
Data Index: 5469222 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.0899. Min Act: -0.1700
Data Index: 2251067 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4024. Min Range: -6.4024
Max Act: 6.1212. Min Act: -0.1700
Data Index: 8411696 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19