Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4470 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0957. Min Range: -8.0957
Max Act: 8.0957. Min Act: -0.1700
Data Index: 4368169 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0957. Min Range: -8.0957
Max Act: 8.0957. Min Act: -0.1700
Data Index: 5677073 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.9082. Min Act: -0.1700
Data Index: 3280878 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.8144. Min Act: -0.1700
Data Index: 445067 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7832. Min Act: -0.1700
Data Index: 3359192 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7832. Min Act: -0.1700
Data Index: 3693336 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7519. Min Act: -0.1700
Data Index: 272795 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7519. Min Act: -0.1700
Data Index: 52482 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7519. Min Act: -0.1700
Data Index: 7716866 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7832. Min Act: -0.1700
Data Index: 3859633 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7832. Min Act: -0.1700
Data Index: 2528416 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7207. Min Act: -0.1700
Data Index: 1318785 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7207. Min Act: -0.1700
Data Index: 1215897 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6894. Min Act: -0.1700
Data Index: 2888615 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.7207. Min Act: -0.1700
Data Index: 3382517 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6582. Min Act: -0.1700
Data Index: 7805586 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6582. Min Act: -0.1700
Data Index: 2198680 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6582. Min Act: -0.1700
Data Index: 5023926 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6582. Min Act: -0.1700
Data Index: 4021086 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0957. Min Range: -8.0957
Max Act: 7.6269. Min Act: -0.1700
Data Index: 2495563 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19