Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5672 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0944. Min Range: -12.0944
Max Act: 12.0944. Min Act: -0.1700
Data Index: 2717288 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0944. Min Range: -12.0944
Max Act: 12.0319. Min Act: -0.1700
Data Index: 4810546 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.9694. Min Act: -0.1700
Data Index: 7795717 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.9069. Min Act: -0.1700
Data Index: 1249409 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.9069. Min Act: -0.1700
Data Index: 7853861 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.8444. Min Act: -0.1700
Data Index: 8166510 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.8444. Min Act: -0.1700
Data Index: 6196776 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.8444. Min Act: -0.1700
Data Index: 744176 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.7194. Min Act: -0.1700
Data Index: 5501298 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.7194. Min Act: -0.1700
Data Index: 7025977 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.6569. Min Act: -0.1700
Data Index: 1420075 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.6569. Min Act: -0.1700
Data Index: 5901135 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.6569. Min Act: -0.1700
Data Index: 1342061 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.6569. Min Act: -0.1700
Data Index: 82878 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.5944. Min Act: -0.1700
Data Index: 8717376 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.6569. Min Act: -0.1700
Data Index: 1134000 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.5944. Min Act: -0.1700
Data Index: 8104477 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.5319. Min Act: -0.1700
Data Index: 4002570 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.5319. Min Act: -0.1700
Data Index: 2997658 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0944. Min Range: -12.0944
Max Act: 11.4694. Min Act: -0.1700
Data Index: 2652553 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19