Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.8593. Min Act: -0.1700
Data Index: 4277774 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.7656. Min Act: -0.1700
Data Index: 5264452 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.7968. Min Act: -0.1700
Data Index: 3977191 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.6093. Min Act: -0.1700
Data Index: 8708620 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.5781. Min Act: -0.1700
Data Index: 5529247 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.5468. Min Act: -0.1700
Data Index: 4525877 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.5156. Min Act: -0.1700
Data Index: 4808070 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.5156. Min Act: -0.1700
Data Index: 5440380 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.4531. Min Act: -0.1700
Data Index: 6715796 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.4218. Min Act: -0.1700
Data Index: 5105376 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3593. Min Act: -0.1700
Data Index: 3915258 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3593. Min Act: -0.1700
Data Index: 721607 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3281. Min Act: -0.1700
Data Index: 5169994 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3906. Min Act: -0.1700
Data Index: 540902 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3281. Min Act: -0.1700
Data Index: 7458873 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3593. Min Act: -0.1700
Data Index: 5905619 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3281. Min Act: -0.1700
Data Index: 7266726 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.3593. Min Act: -0.1700
Data Index: 5951106 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.2968. Min Act: -0.1700
Data Index: 5140727 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8593. Min Range: -7.8593
Max Act: 7.2968. Min Act: -0.1700
Data Index: 1008899 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19