Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1981. Min Range: -8.1981
Max Act: 8.1981. Min Act: -0.1700
Data Index: 2784796 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1981. Min Range: -8.1981
Max Act: 8.1044. Min Act: -0.1700
Data Index: 4022624 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1981. Min Range: -8.1981
Max Act: 8.0106. Min Act: -0.1700
Data Index: 857315 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.9481. Min Act: -0.1700
Data Index: 1658081 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.9481. Min Act: -0.1700
Data Index: 1658082 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.8856. Min Act: -0.1700
Data Index: 7456204 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.8544. Min Act: -0.1700
Data Index: 2655867 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.8544. Min Act: -0.1700
Data Index: 7024090 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.7919. Min Act: -0.1700
Data Index: 6249227 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.8231. Min Act: -0.1700
Data Index: 161916 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.7919. Min Act: -0.1700
Data Index: 8407311 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.7294. Min Act: -0.1700
Data Index: 7178641 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.7606. Min Act: -0.1700
Data Index: 5197786 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6669. Min Act: -0.1700
Data Index: 868048 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.7294. Min Act: -0.1700
Data Index: 683619 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6356. Min Act: -0.1700
Data Index: 431858 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6356. Min Act: -0.1700
Data Index: 4128769 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6356. Min Act: -0.1700
Data Index: 6804221 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6044. Min Act: -0.1700
Data Index: 4410855 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.6044. Min Act: -0.1700
Data Index: 1748507 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19