Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.7419. Min Act: -0.1700
Data Index: 4078976 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.7419. Min Act: -0.1700
Data Index: 7560779 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.7107. Min Act: -0.1700
Data Index: 5202157 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5564049 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5857. Min Act: -0.1700
Data Index: 1470750 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5857. Min Act: -0.1700
Data Index: 4033558 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5857. Min Act: -0.1700
Data Index: 8715906 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5857. Min Act: -0.1700
Data Index: 164850 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5544. Min Act: -0.1700
Data Index: 3853912 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5544. Min Act: -0.1700
Data Index: 4898497 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.5232. Min Act: -0.1700
Data Index: 1725375 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4919. Min Act: -0.1700
Data Index: 2095983 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4919. Min Act: -0.1700
Data Index: 7643859 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4919. Min Act: -0.1700
Data Index: 4011670 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4607. Min Act: -0.1700
Data Index: 8616225 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4607. Min Act: -0.1700
Data Index: 6792168 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4294. Min Act: -0.1700
Data Index: 4723737 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4294. Min Act: -0.1700
Data Index: 3390061 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.4294. Min Act: -0.1700
Data Index: 7942820 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7419. Min Range: -6.7419
Max Act: 6.3982. Min Act: -0.1700
Data Index: 2007465 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19