Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5582 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.4610. Min Act: -0.1700
Data Index: 207266 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3985. Min Act: -0.1700
Data Index: 3316877 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3985. Min Act: -0.1700
Data Index: 8685785 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3360. Min Act: -0.1700
Data Index: 5727856 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3360. Min Act: -0.1700
Data Index: 690847 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3360. Min Act: -0.1700
Data Index: 6717405 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3048. Min Act: -0.1700
Data Index: 7518983 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.3048. Min Act: -0.1700
Data Index: 5505778 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.2423. Min Act: -0.1700
Data Index: 4823488 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.2423. Min Act: -0.1700
Data Index: 1535001 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.2423. Min Act: -0.1700
Data Index: 2880404 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.1798. Min Act: -0.1700
Data Index: 3304392 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.1485. Min Act: -0.1700
Data Index: 7844751 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.1485. Min Act: -0.1700
Data Index: 562098 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.1173. Min Act: -0.1700
Data Index: 1375847 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.0860. Min Act: -0.1700
Data Index: 7518978 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.0860. Min Act: -0.1700
Data Index: 2254608 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.0548. Min Act: -0.1700
Data Index: 3417449 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.0548. Min Act: -0.1700
Data Index: 4547350 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4610. Min Range: -5.4610
Max Act: 5.0548. Min Act: -0.1700
Data Index: 7463863 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19