Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7855. Min Act: -0.1700
Data Index: 8751566 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7855. Min Act: -0.1700
Data Index: 3876703 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.8015. Min Act: -0.1700
Data Index: 7033980 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7537. Min Act: -0.1700
Data Index: 6940468 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7377. Min Act: -0.1700
Data Index: 2922189 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7377. Min Act: -0.1700
Data Index: 769981 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 1615966 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 4525916 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 5788225 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 8277974 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 5840168 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 5313992 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1695
Data Index: 5942933 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 756093 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 8258741 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 5851213 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 6013297 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6897. Min Act: -0.1700
Data Index: 7953684 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7057. Min Act: -0.1700
Data Index: 5870258 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6897. Min Act: -0.1700
Data Index: 6917338 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19