Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 973 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.9131. Min Act: -0.1700
Data Index: 6220836 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.9131. Min Act: -0.1700
Data Index: 6220819 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.7881. Min Act: -0.1700
Data Index: 4362746 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.7256. Min Act: -0.1700
Data Index: 7201250 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.6631. Min Act: -0.1700
Data Index: 4412586 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.6631. Min Act: -0.1700
Data Index: 4362740 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.6006. Min Act: -0.1700
Data Index: 3866415 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.6006. Min Act: -0.1700
Data Index: 922981 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 1026425 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.5381. Min Act: -0.1700
Data Index: 2240650 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.5381. Min Act: -0.1700
Data Index: 4658587 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.5381. Min Act: -0.1700
Data Index: 4658595 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.5381. Min Act: -0.1700
Data Index: 2240654 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 7201255 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 682148 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 4688684 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 4835764 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 3578452 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4756. Min Act: -0.1700
Data Index: 6853589 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9131. Min Range: -9.9131
Max Act: 9.4131. Min Act: -0.1700
Data Index: 520908 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19