Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.9075. Min Act: -0.1700
Data Index: 921726 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.6886. Min Act: -0.1700
Data Index: 7138691 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.6573. Min Act: -0.1700
Data Index: 8563591 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.5321. Min Act: -0.1700
Data Index: 4559887 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.4851. Min Act: -0.1700
Data Index: 392813 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.5008. Min Act: -0.1700
Data Index: 276215 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.4538. Min Act: -0.1700
Data Index: 8597160 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.4224. Min Act: -0.1700
Data Index: 486836 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3911. Min Act: -0.1700
Data Index: 4533989 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.4068. Min Act: -0.1700
Data Index: 521695 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3754. Min Act: -0.1700
Data Index: 5672785 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3754. Min Act: -0.1700
Data Index: 2101054 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3283. Min Act: -0.1700
Data Index: 8058010 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3283. Min Act: -0.1700
Data Index: 7144440 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3126. Min Act: -0.1700
Data Index: 5612738 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3126. Min Act: -0.1700
Data Index: 4174446 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.3126. Min Act: -0.1700
Data Index: 1483423 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.2969. Min Act: -0.1700
Data Index: 5754219 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.2969. Min Act: -0.1700
Data Index: 3722551 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9075. Min Range: -3.9075
Max Act: 3.2655. Min Act: -0.1700
Data Index: 819725 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19