Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.5041. Min Act: -0.1700
Data Index: 4886525 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.3791. Min Act: -0.1700
Data Index: 3160973 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0979. Min Act: -0.1700
Data Index: 3906309 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.1291. Min Act: -0.1700
Data Index: 1926578 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0354. Min Act: -0.1700
Data Index: 7864097 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0041. Min Act: -0.1700
Data Index: 1845801 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0354. Min Act: -0.1700
Data Index: 1053754 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0354. Min Act: -0.1700
Data Index: 6524133 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0354. Min Act: -0.1700
Data Index: 5308453 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5041. Min Range: -8.5041
Max Act: 8.0041. Min Act: -0.1700
Data Index: 6068405 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9729. Min Act: -0.1700
Data Index: 7683791 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9729. Min Act: -0.1700
Data Index: 5186354 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9729. Min Act: -0.1700
Data Index: 8762676 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9729. Min Act: -0.1700
Data Index: 7405722 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9104. Min Act: -0.1700
Data Index: 5659007 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9416. Min Act: -0.1700
Data Index: 5318509 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.9729. Min Act: -0.1700
Data Index: 5328450 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.8479. Min Act: -0.1700
Data Index: 806371 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.8479. Min Act: -0.1700
Data Index: 1498211 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5041. Min Range: -8.5041
Max Act: 7.8166. Min Act: -0.1700
Data Index: 8326362 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19