Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1529 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1290. Min Range: -6.1290
Max Act: 6.1290. Min Act: -0.1700
Data Index: 7095878 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1290. Min Range: -6.1290
Max Act: 6.0978. Min Act: -0.1700
Data Index: 4478884 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.9415. Min Act: -0.1700
Data Index: 5954455 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.9415. Min Act: -0.1700
Data Index: 5396428 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.8790. Min Act: -0.1700
Data Index: 6024450 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.9103. Min Act: -0.1700
Data Index: 1483551 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.8478. Min Act: -0.1700
Data Index: 8435846 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.8790. Min Act: -0.1700
Data Index: 3906591 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.8478. Min Act: -0.1700
Data Index: 6630750 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.8790. Min Act: -0.1700
Data Index: 6522472 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7540. Min Act: -0.1700
Data Index: 8790876 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7853. Min Act: -0.1700
Data Index: 8829454 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7540. Min Act: -0.1700
Data Index: 2736820 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7228. Min Act: -0.1700
Data Index: 22034 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2668027 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7540. Min Act: -0.1700
Data Index: 3214567 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7228. Min Act: -0.1700
Data Index: 4310784 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.6915. Min Act: -0.1700
Data Index: 918003 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7228. Min Act: -0.1700
Data Index: 5780838 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1290. Min Range: -6.1290
Max Act: 5.7228. Min Act: -0.1700
Data Index: 4199796 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19