Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.3928. Min Act: -0.1700
Data Index: 581380 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.3303. Min Act: -0.1700
Data Index: 2416789 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.2678. Min Act: -0.1700
Data Index: 595486 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.2053. Min Act: -0.1700
Data Index: 5941076 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.2053. Min Act: -0.1700
Data Index: 2181331 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.2053. Min Act: -0.1700
Data Index: 3703405 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.2678. Min Act: -0.1700
Data Index: 7562901 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.0803. Min Act: -0.1700
Data Index: 4473385 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3928. Min Range: -12.3928
Max Act: 12.0178. Min Act: -0.1700
Data Index: 7006723 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.8928. Min Act: -0.1700
Data Index: 5531561 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.9553. Min Act: -0.1700
Data Index: 8616453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.9553. Min Act: -0.1700
Data Index: 5367054 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.9553. Min Act: -0.1700
Data Index: 5531548 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.8303. Min Act: -0.1700
Data Index: 7088365 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.8303. Min Act: -0.1700
Data Index: 1823127 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.7053. Min Act: -0.1700
Data Index: 2405090 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.7678. Min Act: -0.1700
Data Index: 581381 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.7678. Min Act: -0.1700
Data Index: 6609164 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.7053. Min Act: -0.1700
Data Index: 1223873 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3928. Min Range: -12.3928
Max Act: 11.7678. Min Act: -0.1700
Data Index: 581376 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19