Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 729 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1746. Min Range: -7.1746
Max Act: 7.1746. Min Act: -0.1700
Data Index: 6723178 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1746. Min Range: -7.1746
Max Act: 7.1121. Min Act: -0.1700
Data Index: 7675405 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1746. Min Range: -7.1746
Max Act: 7.0496. Min Act: -0.1700
Data Index: 1951004 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1746. Min Range: -7.1746
Max Act: 7.0183. Min Act: -0.1700
Data Index: 6429042 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.8621. Min Act: -0.1700
Data Index: 5870041 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8342269 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.8308. Min Act: -0.1700
Data Index: 1059860 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.7058. Min Act: -0.1700
Data Index: 199224 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.6746. Min Act: -0.1700
Data Index: 5745413 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.6433. Min Act: -0.1700
Data Index: 7382095 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.6746. Min Act: -0.1700
Data Index: 6892967 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.6121. Min Act: -0.1700
Data Index: 5413256 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.6121. Min Act: -0.1700
Data Index: 5003274 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5808. Min Act: -0.1700
Data Index: 4020594 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5808. Min Act: -0.1700
Data Index: 3248432 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5496. Min Act: -0.1700
Data Index: 3984764 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5496. Min Act: -0.1700
Data Index: 6397850 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5808. Min Act: -0.1700
Data Index: 4995086 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.5183. Min Act: -0.1700
Data Index: 816671 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1746. Min Range: -7.1746
Max Act: 6.4871. Min Act: -0.1700
Data Index: 3743201 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19