Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.9606. Min Act: -0.1700
Data Index: 5110609 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.5231. Min Act: -0.1700
Data Index: 1473149 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.4606. Min Act: -0.1700
Data Index: 667783 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.2731. Min Act: -0.1700
Data Index: 1856973 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.0856. Min Act: -0.1700
Data Index: 3413534 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.0856. Min Act: -0.1700
Data Index: 3031846 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.0856. Min Act: -0.1700
Data Index: 4907277 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.0856. Min Act: -0.1700
Data Index: 437972 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9606. Min Range: -9.9606
Max Act: 9.0231. Min Act: -0.1700
Data Index: 2246432 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.9606. Min Act: -0.1700
Data Index: 4546900 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.9606. Min Act: -0.1700
Data Index: 179596 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.8981. Min Act: -0.1700
Data Index: 5885371 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.8981. Min Act: -0.1700
Data Index: 5231759 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.8981. Min Act: -0.1700
Data Index: 5639747 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.9606. Min Act: -0.1700
Data Index: 799034 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.7731. Min Act: -0.1700
Data Index: 2601968 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.7731. Min Act: -0.1700
Data Index: 642628 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.7731. Min Act: -0.1700
Data Index: 1604271 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.7731. Min Act: -0.1700
Data Index: 3273375 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9606. Min Range: -9.9606
Max Act: 8.7106. Min Act: -0.1700
Data Index: 5127506 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19