Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2029. Min Range: -5.2029
Max Act: 5.2029. Min Act: -0.1700
Data Index: 5496496 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2029. Min Range: -5.2029
Max Act: 5.0779. Min Act: -0.1700
Data Index: 4943470 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.9216. Min Act: -0.1700
Data Index: 7810755 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.9216. Min Act: -0.1700
Data Index: 7810753 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.9529. Min Act: -0.1700
Data Index: 1028566 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.8904. Min Act: -0.1700
Data Index: 3297936 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.8904. Min Act: -0.1700
Data Index: 5800996 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.8904. Min Act: -0.1700
Data Index: 4163402 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7966. Min Act: -0.1700
Data Index: 3845619 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7966. Min Act: -0.1700
Data Index: 8549154 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.8279. Min Act: -0.1700
Data Index: 1530379 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7966. Min Act: -0.1700
Data Index: 2876344 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7966. Min Act: -0.1700
Data Index: 3854510 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7966. Min Act: -0.1700
Data Index: 3921228 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7029. Min Act: -0.1700
Data Index: 4088717 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7029. Min Act: -0.1700
Data Index: 4088715 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7029. Min Act: -0.1700
Data Index: 3526771 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.7029. Min Act: -0.1700
Data Index: 1988251 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.6716. Min Act: -0.1700
Data Index: 2953309 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2029. Min Range: -5.2029
Max Act: 4.6404. Min Act: -0.1700
Data Index: 5160213 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19