Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7500. Min Act: -0.1700
Data Index: 7050853 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7812. Min Act: -0.1700
Data Index: 2571611 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7187. Min Act: -0.1700
Data Index: 345251 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7343. Min Act: -0.1700
Data Index: 4836161 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7187. Min Act: -0.1700
Data Index: 1843902 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.7030. Min Act: -0.1700
Data Index: 6226983 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6874. Min Act: -0.1700
Data Index: 4777951 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6874. Min Act: -0.1700
Data Index: 2061904 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6561. Min Act: -0.1700
Data Index: 444456 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6561. Min Act: -0.1700
Data Index: 1873474 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6404. Min Act: -0.1700
Data Index: 6404790 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6404. Min Act: -0.1700
Data Index: 1241786 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6404. Min Act: -0.1700
Data Index: 6761854 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6091. Min Act: -0.1700
Data Index: 8745240 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.5935. Min Act: -0.1700
Data Index: 8822254 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.6091. Min Act: -0.1700
Data Index: 547278 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.5935. Min Act: -0.1700
Data Index: 3444034 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.5622. Min Act: -0.1700
Data Index: 6925072 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.5778. Min Act: -0.1700
Data Index: 5631661 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7812. Min Range: -3.7812
Max Act: 3.5622. Min Act: -0.1700
Data Index: 8330827 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19