Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5884 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.7496. Min Act: -0.1700
Data Index: 6930609 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.4059. Min Act: -0.1700
Data Index: 8428846 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.3746. Min Act: -0.1700
Data Index: 2891009 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.3434. Min Act: -0.1700
Data Index: 6577750 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.3434. Min Act: -0.1700
Data Index: 6189371 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.3121. Min Act: -0.1700
Data Index: 1661899 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.2809. Min Act: -0.1700
Data Index: 667931 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.2496. Min Act: -0.1700
Data Index: 7712874 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.2184. Min Act: -0.1700
Data Index: 698420 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.2496. Min Act: -0.1700
Data Index: 2003193 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.1871. Min Act: -0.1700
Data Index: 7811405 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.1559. Min Act: -0.1700
Data Index: 5716477 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.1871. Min Act: -0.1700
Data Index: 4714376 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.1559. Min Act: -0.1700
Data Index: 116436 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.0934. Min Act: -0.1700
Data Index: 4650386 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.0934. Min Act: -0.1700
Data Index: 3697795 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.0621. Min Act: -0.1700
Data Index: 8621022 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.0309. Min Act: -0.1700
Data Index: 6468214 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7496. Min Range: -6.7496
Max Act: 6.0309. Min Act: -0.1700
Data Index: 5304408 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7496. Min Range: -6.7496
Max Act: 5.9996. Min Act: -0.1700
Data Index: 2622693 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19