Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.3218. Min Act: -0.1700
Data Index: 7312219 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.3218. Min Act: -0.1700
Data Index: 1725088 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.2593. Min Act: -0.1700
Data Index: 6327299 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.1968. Min Act: -0.1700
Data Index: 4444331 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.1968. Min Act: -0.1700
Data Index: 699536 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.1343. Min Act: -0.1700
Data Index: 5157574 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0718. Min Act: -0.1700
Data Index: 226821 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.1343. Min Act: -0.1700
Data Index: 2197959 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0718. Min Act: -0.1700
Data Index: 2484978 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0718. Min Act: -0.1700
Data Index: 1140267 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0718. Min Act: -0.1700
Data Index: 1909619 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0718. Min Act: -0.1700
Data Index: 6431109 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0093. Min Act: -0.1700
Data Index: 6253802 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0093. Min Act: -0.1700
Data Index: 1986069 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0093. Min Act: -0.1700
Data Index: 2777040 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0093. Min Act: -0.1700
Data Index: 2493102 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3218. Min Range: -9.3218
Max Act: 9.0093. Min Act: -0.1700
Data Index: 6397926 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3218. Min Range: -9.3218
Max Act: 8.9468. Min Act: -0.1700
Data Index: 5826662 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3218. Min Range: -9.3218
Max Act: 8.8843. Min Act: -0.1700
Data Index: 505498 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3218. Min Range: -9.3218
Max Act: 8.9468. Min Act: -0.1700
Data Index: 1474501 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19