Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.3469. Min Act: -0.1700
Data Index: 695098 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.3469. Min Act: -0.1700
Data Index: 5233034 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.2219. Min Act: -0.1700
Data Index: 1971617 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.2219. Min Act: -0.1700
Data Index: 4662691 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.2219. Min Act: -0.1700
Data Index: 2517367 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.1594. Min Act: -0.1700
Data Index: 6453188 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.1594. Min Act: -0.1700
Data Index: 6918268 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.1594. Min Act: -0.1700
Data Index: 3581128 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.1594. Min Act: -0.1700
Data Index: 8425941 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.1594. Min Act: -0.1700
Data Index: 6488920 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0969. Min Act: -0.1700
Data Index: 4943927 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0969. Min Act: -0.1700
Data Index: 6910896 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0969. Min Act: -0.1700
Data Index: 1847784 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 1922187 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 4598468 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 1590186 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 6417906 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 6060805 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 435686 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3469. Min Range: -11.3469
Max Act: 11.0344. Min Act: -0.1700
Data Index: 6769814 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19