Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4593. Min Range: -7.4593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 802105 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4593. Min Range: -7.4593
Max Act: 7.0218. Min Act: -0.1700
Data Index: 2914292 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.9905. Min Act: -0.1700
Data Index: 781393 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.8030. Min Act: -0.1700
Data Index: 5278886 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.7405. Min Act: -0.1700
Data Index: 906685 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.7093. Min Act: -0.1700
Data Index: 1048140 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.7405. Min Act: -0.1700
Data Index: 6569795 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.7093. Min Act: -0.1700
Data Index: 634334 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6780. Min Act: -0.1700
Data Index: 1404106 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6780. Min Act: -0.1700
Data Index: 129009 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6155. Min Act: -0.1700
Data Index: 6538017 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6155. Min Act: -0.1700
Data Index: 5374208 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6155. Min Act: -0.1700
Data Index: 4620657 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.6155. Min Act: -0.1700
Data Index: 6462056 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5530. Min Act: -0.1700
Data Index: 7660338 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5530. Min Act: -0.1700
Data Index: 2772293 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5530. Min Act: -0.1700
Data Index: 8698358 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5530. Min Act: -0.1700
Data Index: 8499284 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5218. Min Act: -0.1700
Data Index: 3298399 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4593. Min Range: -7.4593
Max Act: 6.5218. Min Act: -0.1700
Data Index: 7858810 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19