Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.3569. Min Act: -0.1700
Data Index: 3020029 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.3882. Min Act: -0.1700
Data Index: 4169664 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.3257. Min Act: -0.1700
Data Index: 3418759 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.3569. Min Act: -0.1700
Data Index: 8385295 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.2944. Min Act: -0.1700
Data Index: 8770646 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.2319. Min Act: -0.1700
Data Index: 3622960 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.2007. Min Act: -0.1698
Data Index: 6252267 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.1694. Min Act: -0.1700
Data Index: 5085881 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.1694. Min Act: -0.1700
Data Index: 6560563 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.1694. Min Act: -0.1700
Data Index: 5235946 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.1069. Min Act: -0.1700
Data Index: 2912406 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.1069. Min Act: -0.1700
Data Index: 6426684 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1700
Data Index: 870366 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1700
Data Index: 6426672 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1700
Data Index: 5300541 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1700
Data Index: 3801547 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1698
Data Index: 6252276 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0757. Min Act: -0.1698
Data Index: 6476389 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0444. Min Act: -0.1700
Data Index: 1218244 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3882. Min Range: -7.3882
Max Act: 7.0132. Min Act: -0.1700
Data Index: 2088728 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19