Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.1575. Min Act: -0.1700
Data Index: 2371493 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.1575. Min Act: -0.1700
Data Index: 3018797 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.1575. Min Act: -0.1700
Data Index: 2371494 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.1887. Min Act: -0.1700
Data Index: 8599068 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.0950. Min Act: -0.1700
Data Index: 1152994 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.0325. Min Act: -0.1700
Data Index: 1306473 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.0325. Min Act: -0.1700
Data Index: 1663911 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1887. Min Range: -8.1887
Max Act: 8.0012. Min Act: -0.1700
Data Index: 3242949 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9700. Min Act: -0.1700
Data Index: 5061762 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9700. Min Act: -0.1700
Data Index: 7325625 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9387. Min Act: -0.1700
Data Index: 5901851 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9387. Min Act: -0.1700
Data Index: 6276590 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9700. Min Act: -0.1700
Data Index: 8622234 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9075. Min Act: -0.1700
Data Index: 6423243 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.8762. Min Act: -0.1700
Data Index: 7511411 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.9075. Min Act: -0.1700
Data Index: 8042113 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.8762. Min Act: -0.1700
Data Index: 8132365 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.8762. Min Act: -0.1700
Data Index: 1716937 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.8450. Min Act: -0.1700
Data Index: 2313782 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1887. Min Range: -8.1887
Max Act: 7.8762. Min Act: -0.1700
Data Index: 5202146 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19