Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4914 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.7909. Min Act: -0.1700
Data Index: 3366070 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.6659. Min Act: -0.1700
Data Index: 6199517 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.5721. Min Act: -0.1700
Data Index: 5558671 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.5721. Min Act: -0.1700
Data Index: 994134 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.4784. Min Act: -0.1700
Data Index: 1449234 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.4159. Min Act: -0.1700
Data Index: 3745745 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.4159. Min Act: -0.1700
Data Index: 2469577 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.3534. Min Act: -0.1700
Data Index: 1314521 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1971. Min Act: -0.1700
Data Index: 8469632 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1971. Min Act: -0.1700
Data Index: 3957991 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1971. Min Act: -0.1700
Data Index: 1528996 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1971. Min Act: -0.1700
Data Index: 1873924 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1034. Min Act: -0.1700
Data Index: 4944755 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1659. Min Act: -0.1700
Data Index: 8636175 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.1034. Min Act: -0.1700
Data Index: 2017196 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.0721. Min Act: -0.1700
Data Index: 4178342 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.0721. Min Act: -0.1700
Data Index: 1301354 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.0721. Min Act: -0.1700
Data Index: 3425629 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.0721. Min Act: -0.1700
Data Index: 5174898 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7909. Min Range: -7.7909
Max Act: 7.0409. Min Act: -0.1700
Data Index: 3173521 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19