Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3121. Min Range: -8.3121
Max Act: 8.3121. Min Act: -0.1700
Data Index: 2153715 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3121. Min Range: -8.3121
Max Act: 8.1871. Min Act: -0.1700
Data Index: 3049016 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3121. Min Range: -8.3121
Max Act: 8.1559. Min Act: -0.1700
Data Index: 2023801 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3121. Min Range: -8.3121
Max Act: 8.0309. Min Act: -0.1700
Data Index: 5288541 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3121. Min Range: -8.3121
Max Act: 8.0309. Min Act: -0.1700
Data Index: 361435 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.8434. Min Act: -0.1700
Data Index: 8644491 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.8746. Min Act: -0.1700
Data Index: 5677023 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.8434. Min Act: -0.1700
Data Index: 6815664 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.7809. Min Act: -0.1700
Data Index: 4441697 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.7184. Min Act: -0.1700
Data Index: 5556011 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.6246. Min Act: -0.1700
Data Index: 379948 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6606800 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6706720 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.5309. Min Act: -0.1700
Data Index: 267105 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4996. Min Act: -0.1700
Data Index: 3767653 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4996. Min Act: -0.1700
Data Index: 2909565 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4684. Min Act: -0.1700
Data Index: 2053745 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4371. Min Act: -0.1700
Data Index: 4773458 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4059. Min Act: -0.1700
Data Index: 1660709 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3121. Min Range: -8.3121
Max Act: 7.4059. Min Act: -0.1700
Data Index: 7554878 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19