Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2822. Min Range: -8.2822
Max Act: 8.2822. Min Act: -0.1700
Data Index: 6193965 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2822. Min Range: -8.2822
Max Act: 8.1885. Min Act: -0.1700
Data Index: 5293188 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.8760. Min Act: -0.1700
Data Index: 6285592 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.8135. Min Act: -0.1700
Data Index: 604747 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.8135. Min Act: -0.1700
Data Index: 1540040 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.7197. Min Act: -0.1700
Data Index: 8727884 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.6885. Min Act: -0.1700
Data Index: 5284339 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.5322. Min Act: -0.1700
Data Index: 5159455 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.5010. Min Act: -0.1700
Data Index: 2003501 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4697. Min Act: -0.1700
Data Index: 4052514 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4697. Min Act: -0.1700
Data Index: 7492809 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4697. Min Act: -0.1700
Data Index: 2235236 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.3760. Min Act: -0.1700
Data Index: 2555522 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4072. Min Act: -0.1700
Data Index: 8674000 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4385. Min Act: -0.1700
Data Index: 4462626 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.4072. Min Act: -0.1700
Data Index: 375913 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.3760. Min Act: -0.1700
Data Index: 974527 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.3447. Min Act: -0.1700
Data Index: 1204578 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.3447. Min Act: -0.1700
Data Index: 6691892 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2822. Min Range: -8.2822
Max Act: 7.2822. Min Act: -0.1700
Data Index: 1473427 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19