Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5872 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6407. Min Range: -7.6407
Max Act: 7.6407. Min Act: -0.1700
Data Index: 5436713 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6407. Min Range: -7.6407
Max Act: 7.2344. Min Act: -0.1700
Data Index: 4728820 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6407. Min Range: -7.6407
Max Act: 7.1719. Min Act: -0.1700
Data Index: 7627209 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6407. Min Range: -7.6407
Max Act: 7.0782. Min Act: -0.1700
Data Index: 8271282 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6407. Min Range: -7.6407
Max Act: 7.0469. Min Act: -0.1700
Data Index: 390527 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8907. Min Act: -0.1700
Data Index: 4589059 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8907. Min Act: -0.1700
Data Index: 8433122 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8594. Min Act: -0.1700
Data Index: 1104022 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8594. Min Act: -0.1700
Data Index: 5973491 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8282. Min Act: -0.1700
Data Index: 1104016 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8282. Min Act: -0.1700
Data Index: 7772062 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.8282. Min Act: -0.1700
Data Index: 6173000 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 5096457 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 3142423 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 6680782 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 1928174 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 1513496 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 5019260 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7657. Min Act: -0.1700
Data Index: 1967880 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6407. Min Range: -7.6407
Max Act: 6.7969. Min Act: -0.1700
Data Index: 1322959 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19