Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1277 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.2880. Min Act: -0.1700
Data Index: 321448 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.2880. Min Act: -0.1700
Data Index: 7902112 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1942. Min Act: -0.1700
Data Index: 5887871 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.2255. Min Act: -0.1700
Data Index: 1325114 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.2255. Min Act: -0.1700
Data Index: 254114 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1942. Min Act: -0.1700
Data Index: 1266462 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1630. Min Act: -0.1700
Data Index: 3648500 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1317. Min Act: -0.1700
Data Index: 722722 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1317. Min Act: -0.1700
Data Index: 951832 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.1005. Min Act: -0.1700
Data Index: 7487794 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0692. Min Act: -0.1700
Data Index: 2383661 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0380. Min Act: -0.1700
Data Index: 5887869 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0380. Min Act: -0.1700
Data Index: 3292915 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0380. Min Act: -0.1700
Data Index: 790972 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0380. Min Act: -0.1700
Data Index: 5749090 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0380. Min Act: -0.1700
Data Index: 5152462 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0067. Min Act: -0.1700
Data Index: 4337578 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2880. Min Range: -4.2880
Max Act: 4.0067. Min Act: -0.1700
Data Index: 8060018 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2880. Min Range: -4.2880
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5936887 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2880. Min Range: -4.2880
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5252675 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19