Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.5183. Min Act: -0.1700
Data Index: 6179104 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.3772. Min Act: -0.1700
Data Index: 6702682 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.3459. Min Act: -0.1700
Data Index: 6110723 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.3145. Min Act: -0.1700
Data Index: 8370679 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.2988. Min Act: -0.1700
Data Index: 4264044 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.2517. Min Act: -0.1700
Data Index: 6497252 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.2045. Min Act: -0.1700
Data Index: 8124414 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.2045. Min Act: -0.1700
Data Index: 8575739 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1730. Min Act: -0.1700
Data Index: 7206062 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1730. Min Act: -0.1700
Data Index: 6018621 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1573. Min Act: -0.1700
Data Index: 7709012 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1573. Min Act: -0.1700
Data Index: 2727975 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1416. Min Act: -0.1700
Data Index: 3480543 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1573. Min Act: -0.1700
Data Index: 7098694 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1573. Min Act: -0.1700
Data Index: 1184756 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1416. Min Act: -0.1700
Data Index: 7313750 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1258. Min Act: -0.1700
Data Index: 1998946 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1730. Min Act: -0.1700
Data Index: 218415 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1416. Min Act: -0.1700
Data Index: 4588603 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5183. Min Range: -3.5183
Max Act: 3.1101. Min Act: -0.1700
Data Index: 1147539 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19