Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 442 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.9988. Min Act: -0.1700
Data Index: 248504 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.6238. Min Act: -0.1699
Data Index: 7645015 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.5301. Min Act: -0.1699
Data Index: 1989437 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.5301. Min Act: -0.1700
Data Index: 2707732 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4676. Min Act: -0.1700
Data Index: 295511 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4363. Min Act: -0.1700
Data Index: 6970040 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 345902 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4363. Min Act: -0.1700
Data Index: 4447642 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 2175627 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6510329 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6720150 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4791526 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 5931678 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3426. Min Act: -0.1700
Data Index: 8827133 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3426. Min Act: -0.1700
Data Index: 7040865 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3426. Min Act: -0.1699
Data Index: 5290661 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 2763560 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 2523313 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1119240 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9988. Min Range: -5.9988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1270853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19