Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.3075. Min Act: -0.1700
Data Index: 4819018 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.3075. Min Act: -0.1700
Data Index: 4334844 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.2449. Min Act: -0.1700
Data Index: 6537038 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.2449. Min Act: -0.1700
Data Index: 3633715 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.2449. Min Act: -0.1700
Data Index: 6931416 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1824. Min Act: -0.1700
Data Index: 4869933 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1512. Min Act: -0.1700
Data Index: 3601830 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1512. Min Act: -0.1700
Data Index: 5343339 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1199. Min Act: -0.1700
Data Index: 8607850 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1199. Min Act: -0.1700
Data Index: 8764537 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1512. Min Act: -0.1700
Data Index: 4311115 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.1199. Min Act: -0.1700
Data Index: 2824764 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3075. Min Range: -4.3075
Max Act: 3.9949. Min Act: -0.1700
Data Index: 1708815 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0887. Min Act: -0.1700
Data Index: 417813 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0574. Min Act: -0.1700
Data Index: 396955 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0574. Min Act: -0.1700
Data Index: 4973248 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0574. Min Act: -0.1700
Data Index: 4173473 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0262. Min Act: -0.1700
Data Index: 6174327 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3075. Min Range: -4.3075
Max Act: 4.0262. Min Act: -0.1700
Data Index: 8604925 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3075. Min Range: -4.3075
Max Act: 3.9949. Min Act: -0.1700
Data Index: 7298068 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19