Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.6097. Min Act: -0.1700
Data Index: 956369 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.5472. Min Act: -0.1700
Data Index: 5344321 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.5160. Min Act: -0.1700
Data Index: 1497640 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.4535. Min Act: -0.1700
Data Index: 3806021 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3910. Min Act: -0.1700
Data Index: 8333049 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3910. Min Act: -0.1700
Data Index: 2481174 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3597. Min Act: -0.1700
Data Index: 2084800 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5589384 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3285. Min Act: -0.1700
Data Index: 2895126 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 3387682 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5143888 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 6527292 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2660. Min Act: -0.1700
Data Index: 2064172 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 2715639 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7938163 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7566302 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 1735558 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7056974 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2660. Min Act: -0.1700
Data Index: 6977463 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6097. Min Range: -5.6097
Max Act: 5.2660. Min Act: -0.1700
Data Index: 3975114 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19