Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.8395. Min Act: -0.1700
Data Index: 7593994 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.6520. Min Act: -0.1700
Data Index: 424074 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.6208. Min Act: -0.1700
Data Index: 2772827 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.6208. Min Act: -0.1700
Data Index: 6726041 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 8768571 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 6541681 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5895. Min Act: -0.1700
Data Index: 903822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 8396918 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5895. Min Act: -0.1700
Data Index: 4799191 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 2234856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 2689223 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 7558619 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6762351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 3162776 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 3162777 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 7594371 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4958. Min Act: -0.1700
Data Index: 6008897 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 8178987 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5583. Min Act: -0.1700
Data Index: 701368 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 3878678 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19