Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5103 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.9011. Min Act: -0.1700
Data Index: 6340806 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.6824. Min Act: -0.1700
Data Index: 3684735 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.3699. Min Act: -0.1700
Data Index: 326804 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.3074. Min Act: -0.1700
Data Index: 7053295 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.2761. Min Act: -0.1700
Data Index: 6017396 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.2449. Min Act: -0.1700
Data Index: 4205766 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.1511. Min Act: -0.1700
Data Index: 4804814 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.1199. Min Act: -0.1700
Data Index: 1168528 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.1199. Min Act: -0.1700
Data Index: 6758431 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.0886. Min Act: -0.1700
Data Index: 389295 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.0574. Min Act: -0.1700
Data Index: 2247899 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9011. Min Range: -6.9011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 3761329 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9949. Min Act: -0.1700
Data Index: 7258034 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9949. Min Act: -0.1700
Data Index: 1129040 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9949. Min Act: -0.1700
Data Index: 8419596 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9324. Min Act: -0.1700
Data Index: 5378807 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9324. Min Act: -0.1700
Data Index: 3706848 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9636. Min Act: -0.1700
Data Index: 1867890 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9324. Min Act: -0.1700
Data Index: 4217192 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9011. Min Range: -6.9011
Max Act: 5.9324. Min Act: -0.1700
Data Index: 5183051 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19