Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5482. Min Range: -9.5482
Max Act: 9.5482. Min Act: -0.1700
Data Index: 6794230 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5482. Min Range: -9.5482
Max Act: 9.2982. Min Act: -0.1700
Data Index: 689611 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5482. Min Range: -9.5482
Max Act: 9.1732. Min Act: -0.1700
Data Index: 1627454 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.9232. Min Act: -0.1700
Data Index: 7364744 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.8607. Min Act: -0.1700
Data Index: 1730208 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7982. Min Act: -0.1700
Data Index: 4631126 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7357. Min Act: -0.1700
Data Index: 7228997 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7357. Min Act: -0.1700
Data Index: 7350679 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7357. Min Act: -0.1700
Data Index: 4026223 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7357. Min Act: -0.1700
Data Index: 749418 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.7357. Min Act: -0.1700
Data Index: 8449422 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.6732. Min Act: -0.1700
Data Index: 4661427 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.6107. Min Act: -0.1700
Data Index: 5036643 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.6107. Min Act: -0.1700
Data Index: 8602083 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.6107. Min Act: -0.1700
Data Index: 4642089 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.6107. Min Act: -0.1700
Data Index: 1575845 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.4857. Min Act: -0.1700
Data Index: 4343066 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.5482. Min Act: -0.1700
Data Index: 3237917 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.5482. Min Act: -0.1700
Data Index: 2490047 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5482. Min Range: -9.5482
Max Act: 8.4857. Min Act: -0.1700
Data Index: 3429303 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19