Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4617. Min Range: -9.4617
Max Act: 9.4617. Min Act: -0.1700
Data Index: 7571341 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4617. Min Range: -9.4617
Max Act: 9.3992. Min Act: -0.1700
Data Index: 7442350 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4617. Min Range: -9.4617
Max Act: 9.3992. Min Act: -0.1700
Data Index: 1252786 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4617. Min Range: -9.4617
Max Act: 9.2117. Min Act: -0.1700
Data Index: 309720 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.9617. Min Act: -0.1700
Data Index: 1387164 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.8992. Min Act: -0.1700
Data Index: 1706866 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.8367. Min Act: -0.1700
Data Index: 566136 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.7742. Min Act: -0.1700
Data Index: 3026571 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.7742. Min Act: -0.1700
Data Index: 3532979 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.7742. Min Act: -0.1700
Data Index: 2366903 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.7117. Min Act: -0.1700
Data Index: 960748 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.7117. Min Act: -0.1700
Data Index: 2177106 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5867. Min Act: -0.1700
Data Index: 1266352 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.6492. Min Act: -0.1700
Data Index: 4006455 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.6492. Min Act: -0.1700
Data Index: 2946928 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5242. Min Act: -0.1700
Data Index: 3755248 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5867. Min Act: -0.1700
Data Index: 5043860 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5242. Min Act: -0.1700
Data Index: 4970557 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5867. Min Act: -0.1700
Data Index: 445072 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4617. Min Range: -9.4617
Max Act: 8.5867. Min Act: -0.1700
Data Index: 5177976 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19