Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0327. Min Range: -8.0327
Max Act: 8.0327. Min Act: -0.1700
Data Index: 1854566 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.8452. Min Act: -0.1700
Data Index: 892936 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.8140. Min Act: -0.1700
Data Index: 724186 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.7515. Min Act: -0.1700
Data Index: 1854571 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.7202. Min Act: -0.1700
Data Index: 20798 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.7202. Min Act: -0.1700
Data Index: 2228857 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.7202. Min Act: -0.1700
Data Index: 7166297 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.6265. Min Act: -0.1700
Data Index: 207769 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5952. Min Act: -0.1700
Data Index: 771980 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5327. Min Act: -0.1700
Data Index: 7379086 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5015. Min Act: -0.1700
Data Index: 4328573 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5327. Min Act: -0.1700
Data Index: 3104272 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5327. Min Act: -0.1700
Data Index: 1094741 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.4702. Min Act: -0.1700
Data Index: 4924038 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5015. Min Act: -0.1700
Data Index: 7379085 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.5015. Min Act: -0.1700
Data Index: 1540261 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.4702. Min Act: -0.1700
Data Index: 2461575 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.4702. Min Act: -0.1700
Data Index: 6575686 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.4390. Min Act: -0.1700
Data Index: 4791882 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0327. Min Range: -8.0327
Max Act: 7.4702. Min Act: -0.1700
Data Index: 7073960 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19