Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.5286. Min Act: -0.1700
Data Index: 3848373 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.4036. Min Act: -0.1700
Data Index: 4794902 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7018074 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.3098. Min Act: -0.1700
Data Index: 561616 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2786. Min Act: -0.1700
Data Index: 895710 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2786. Min Act: -0.1700
Data Index: 4363236 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2473. Min Act: -0.1700
Data Index: 4888820 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2786. Min Act: -0.1700
Data Index: 4976885 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2161. Min Act: -0.1700
Data Index: 5984011 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2473. Min Act: -0.1700
Data Index: 2443527 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2161. Min Act: -0.1700
Data Index: 6564839 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2473. Min Act: -0.1700
Data Index: 378764 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.2161. Min Act: -0.1700
Data Index: 3625623 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1536. Min Act: -0.1700
Data Index: 5544582 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1848. Min Act: -0.1700
Data Index: 1473773 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1848. Min Act: -0.1700
Data Index: 1095750 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1536. Min Act: -0.1700
Data Index: 2703871 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1536. Min Act: -0.1700
Data Index: 6991009 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1536. Min Act: -0.1700
Data Index: 2514565 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5286. Min Range: -4.5286
Max Act: 4.1536. Min Act: -0.1700
Data Index: 2462079 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19