Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.9911. Min Act: -0.1700
Data Index: 2791168 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.9286. Min Act: -0.1700
Data Index: 7817928 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.9286. Min Act: -0.1700
Data Index: 5510645 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8973. Min Act: -0.1700
Data Index: 2189849 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8661. Min Act: -0.1700
Data Index: 3973423 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8348. Min Act: -0.1700
Data Index: 7387240 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8348. Min Act: -0.1700
Data Index: 5641132 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8661. Min Act: -0.1700
Data Index: 8690187 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8348. Min Act: -0.1700
Data Index: 4401835 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8348. Min Act: -0.1700
Data Index: 5213954 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8348. Min Act: -0.1700
Data Index: 7817925 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8036. Min Act: -0.1700
Data Index: 595550 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7723. Min Act: -0.1700
Data Index: 406517 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.8036. Min Act: -0.1700
Data Index: 3170921 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7723. Min Act: -0.1700
Data Index: 7391110 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7411. Min Act: -0.1700
Data Index: 8227914 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7411. Min Act: -0.1700
Data Index: 7851573 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7411. Min Act: -0.1700
Data Index: 7081170 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7411. Min Act: -0.1700
Data Index: 3553961 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9911. Min Range: -4.9911
Max Act: 4.7411. Min Act: -0.1700
Data Index: 3713790 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19