Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.7173. Min Act: -0.1700
Data Index: 7683193 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.7173. Min Act: -0.1700
Data Index: 787136 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6853. Min Act: -0.1700
Data Index: 3327868 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6692. Min Act: -0.1700
Data Index: 7652549 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6532. Min Act: -0.1699
Data Index: 1728217 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6532. Min Act: -0.1700
Data Index: 6409296 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6532. Min Act: -0.1700
Data Index: 6409277 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6211. Min Act: -0.1700
Data Index: 5677614 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6692. Min Act: -0.1700
Data Index: 5677610 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6050. Min Act: -0.1700
Data Index: 5420129 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6211. Min Act: -0.1700
Data Index: 5677598 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.6050. Min Act: -0.1700
Data Index: 3622669 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5889. Min Act: -0.1700
Data Index: 6349093 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5728. Min Act: -0.1700
Data Index: 1233496 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5728. Min Act: -0.1700
Data Index: 286403 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5728. Min Act: -0.1700
Data Index: 6349108 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5405. Min Act: -0.1700
Data Index: 6349091 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5405. Min Act: -0.1700
Data Index: 3809595 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5405. Min Act: -0.1700
Data Index: 5037971 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7173. Min Range: -2.7173
Max Act: 2.5728. Min Act: -0.1700
Data Index: 472242 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19