Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4706. Min Act: -0.1700
Data Index: 7800993 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4706. Min Act: -0.1700
Data Index: 3779393 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 8346542 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 1819758 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 3307404 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4394. Min Act: -0.1700
Data Index: 7760393 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4034601 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4986686 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 5222677 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 3431945 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 8574722 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 6134026 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.4081. Min Act: -0.1700
Data Index: 6760276 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3769. Min Act: -0.1700
Data Index: 65946 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3769. Min Act: -0.1700
Data Index: 3818467 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3769. Min Act: -0.1700
Data Index: 384675 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3769. Min Act: -0.1700
Data Index: 3018534 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3456. Min Act: -0.1700
Data Index: 7164006 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3456. Min Act: -0.1700
Data Index: 6019142 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4706. Min Range: -5.4706
Max Act: 5.3456. Min Act: -0.1700
Data Index: 519947 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19