Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.6722. Min Act: -0.1700
Data Index: 5205145 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.4847. Min Act: -0.1700
Data Index: 1583771 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 5316947 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 3987753 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 2030747 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 5023544 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2347. Min Act: -0.1700
Data Index: 5739470 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1722. Min Act: -0.1700
Data Index: 1202265 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 1603391 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 3543766 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 8708557 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 8186769 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 6868812 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 6271797 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 3097142 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 5810663 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 4941999 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 123671 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 3924404 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 1711160 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19