Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1969. Min Range: -7.1969
Max Act: 7.1969. Min Act: -0.1700
Data Index: 3830446 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1969. Min Range: -7.1969
Max Act: 7.0719. Min Act: -0.1700
Data Index: 6369838 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1969. Min Range: -7.1969
Max Act: 7.0406. Min Act: -0.1700
Data Index: 1086639 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.9781. Min Act: -0.1700
Data Index: 6872310 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.9781. Min Act: -0.1700
Data Index: 2088568 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1969. Min Range: -7.1969
Max Act: 7.0094. Min Act: -0.1700
Data Index: 8488690 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.9781. Min Act: -0.1700
Data Index: 8662747 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.8531. Min Act: -0.1700
Data Index: 7604307 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.8531. Min Act: -0.1700
Data Index: 3098920 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.7906. Min Act: -0.1700
Data Index: 7209881 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.7594. Min Act: -0.1700
Data Index: 8241679 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.7594. Min Act: -0.1700
Data Index: 293564 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6969. Min Act: -0.1700
Data Index: 6724202 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6969. Min Act: -0.1700
Data Index: 4105336 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6969. Min Act: -0.1700
Data Index: 197116 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6344. Min Act: -0.1700
Data Index: 6028229 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6344. Min Act: -0.1700
Data Index: 6473581 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7182901 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6031. Min Act: -0.1700
Data Index: 1362992 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1969. Min Range: -7.1969
Max Act: 6.6031. Min Act: -0.1700
Data Index: 2214003 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19