Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4903 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.5384. Min Act: -0.1700
Data Index: 1944313 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4759. Min Act: -0.1700
Data Index: 8684270 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.5071. Min Act: -0.1700
Data Index: 4583698 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2733292 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4134. Min Act: -0.1700
Data Index: 4914553 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4134. Min Act: -0.1700
Data Index: 8657897 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4134. Min Act: -0.1700
Data Index: 4676450 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 758296 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 8379053 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 7656639 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1946. Min Act: -0.1700
Data Index: 8424118 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1946. Min Act: -0.1700
Data Index: 820529 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1946. Min Act: -0.1700
Data Index: 1121617 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1321. Min Act: -0.1700
Data Index: 6023815 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1634. Min Act: -0.1700
Data Index: 3377859 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1634. Min Act: -0.1700
Data Index: 5258447 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1634. Min Act: -0.1700
Data Index: 6630718 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1634. Min Act: -0.1700
Data Index: 5444072 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1321. Min Act: -0.1700
Data Index: 4333924 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1321. Min Act: -0.1700
Data Index: 4866179 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19