Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5059. Min Range: -8.5059
Max Act: 8.5059. Min Act: -0.1700
Data Index: 1818100 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5059. Min Range: -8.5059
Max Act: 8.1309. Min Act: -0.1700
Data Index: 4828243 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5059. Min Range: -8.5059
Max Act: 8.0372. Min Act: -0.1700
Data Index: 146389 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5059. Min Range: -8.5059
Max Act: 8.0059. Min Act: -0.1700
Data Index: 2297155 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.8809. Min Act: -0.1700
Data Index: 3644913 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.8497. Min Act: -0.1700
Data Index: 234912 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.8497. Min Act: -0.1700
Data Index: 1948570 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.8184. Min Act: -0.1700
Data Index: 2131034 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 8751190 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 1608407 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.7247. Min Act: -0.1700
Data Index: 3245286 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6934. Min Act: -0.1700
Data Index: 7272180 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6622. Min Act: -0.1700
Data Index: 8134944 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 2822126 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 880897 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 1854933 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 7970200 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6622. Min Act: -0.1700
Data Index: 597352 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 6957486 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5059. Min Range: -8.5059
Max Act: 7.5372. Min Act: -0.1700
Data Index: 1543249 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19