Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1996. Min Range: -8.1996
Max Act: 8.1996. Min Act: -0.1700
Data Index: 5482010 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1996. Min Range: -8.1996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 1145712 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1996. Min Range: -8.1996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 7928803 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.8871. Min Act: -0.1700
Data Index: 6974567 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.7621. Min Act: -0.1700
Data Index: 7474833 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.6996. Min Act: -0.1700
Data Index: 2100639 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.6371. Min Act: -0.1700
Data Index: 7953817 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.5746. Min Act: -0.1700
Data Index: 5169035 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.5746. Min Act: -0.1700
Data Index: 5210539 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.5433. Min Act: -0.1700
Data Index: 4593361 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.5121. Min Act: -0.1700
Data Index: 3333391 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4496. Min Act: -0.1700
Data Index: 1643878 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4183. Min Act: -0.1700
Data Index: 1920787 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4496. Min Act: -0.1700
Data Index: 2123268 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4183. Min Act: -0.1700
Data Index: 7801650 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.3871. Min Act: -0.1700
Data Index: 2073452 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4183. Min Act: -0.1700
Data Index: 6026270 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4183. Min Act: -0.1700
Data Index: 4842039 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.4183. Min Act: -0.1699
Data Index: 3376813 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1996. Min Range: -8.1996
Max Act: 7.3558. Min Act: -0.1700
Data Index: 2298585 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19