Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4575 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.9667. Min Act: -0.1700
Data Index: 7826667 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.9242. Min Act: -0.1700
Data Index: 2661401 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8645. Min Act: -0.1700
Data Index: 1538744 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8559. Min Act: -0.1700
Data Index: 2055817 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8473. Min Act: -0.1700
Data Index: 8095140 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8473. Min Act: -0.1700
Data Index: 5551411 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8473. Min Act: -0.1699
Data Index: 1333876 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8473. Min Act: -0.1700
Data Index: 6374389 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8302. Min Act: -0.1700
Data Index: 7617923 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8216. Min Act: -0.1700
Data Index: 8088247 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8302. Min Act: -0.1700
Data Index: 1811928 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8302. Min Act: -0.1700
Data Index: 5745818 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8216. Min Act: -0.1700
Data Index: 1863201 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8044. Min Act: -0.1700
Data Index: 7875970 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8044. Min Act: -0.1700
Data Index: 828109 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8044. Min Act: -0.1700
Data Index: 6973893 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.8044. Min Act: -0.1700
Data Index: 8396230 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.7958. Min Act: -0.1700
Data Index: 3871973 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.7958. Min Act: -0.1700
Data Index: 3427063 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9667. Min Range: -1.9667
Max Act: 1.7786. Min Act: -0.1700
Data Index: 6283262 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19