Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7539. Min Range: -7.7539
Max Act: 7.7539. Min Act: -0.1700
Data Index: 6488639 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7539. Min Range: -7.7539
Max Act: 7.5039. Min Act: -0.1700
Data Index: 6470581 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7539. Min Range: -7.7539
Max Act: 7.4414. Min Act: -0.1700
Data Index: 1086658 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7539. Min Range: -7.7539
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6470580 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7539. Min Range: -7.7539
Max Act: 7.0039. Min Act: -0.1700
Data Index: 8745436 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.9414. Min Act: -0.1700
Data Index: 8117019 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.8789. Min Act: -0.1700
Data Index: 5389884 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.8164. Min Act: -0.1700
Data Index: 2354763 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.8476. Min Act: -0.1700
Data Index: 8745438 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.7851. Min Act: -0.1700
Data Index: 6977055 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.8164. Min Act: -0.1700
Data Index: 3622280 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.7851. Min Act: -0.1700
Data Index: 5309542 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.7851. Min Act: -0.1700
Data Index: 5557041 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.7226. Min Act: -0.1700
Data Index: 7122410 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6576413 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.6914. Min Act: -0.1700
Data Index: 8382414 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.6601. Min Act: -0.1700
Data Index: 232539 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4381254 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.6914. Min Act: -0.1700
Data Index: 7264871 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7539. Min Range: -7.7539
Max Act: 6.6601. Min Act: -0.1700
Data Index: 3191101 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19