Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.7305. Min Act: -0.1700
Data Index: 2867615 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6993. Min Act: -0.1700
Data Index: 2625743 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6680. Min Act: -0.1700
Data Index: 5546759 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6836. Min Act: -0.1700
Data Index: 6691623 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6680. Min Act: -0.1700
Data Index: 4859897 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6367. Min Act: -0.1700
Data Index: 7000106 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6210. Min Act: -0.1700
Data Index: 3413913 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6054. Min Act: -0.1700
Data Index: 7828453 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.6054. Min Act: -0.1700
Data Index: 7828452 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5897. Min Act: -0.1700
Data Index: 4959455 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5897. Min Act: -0.1700
Data Index: 3317594 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5741. Min Act: -0.1700
Data Index: 7999131 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5584. Min Act: -0.1700
Data Index: 3580699 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5584. Min Act: -0.1700
Data Index: 1348246 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5584. Min Act: -0.1700
Data Index: 667257 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5741. Min Act: -0.1700
Data Index: 667260 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5584. Min Act: -0.1700
Data Index: 541115 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5271. Min Act: -0.1700
Data Index: 6681991 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5428. Min Act: -0.1700
Data Index: 5830767 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7305. Min Range: -3.7305
Max Act: 3.5428. Min Act: -0.1700
Data Index: 6183090 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19