Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0401. Min Range: -6.0401
Max Act: 6.0401. Min Act: -0.1700
Data Index: 766287 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0401. Min Range: -6.0401
Max Act: 6.0088. Min Act: -0.1700
Data Index: 3314058 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.9151. Min Act: -0.1700
Data Index: 2316273 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.8838. Min Act: -0.1700
Data Index: 3420912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.8838. Min Act: -0.1700
Data Index: 6211545 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.8213. Min Act: -0.1700
Data Index: 6808068 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.7901. Min Act: -0.1700
Data Index: 2553136 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6785933 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.7588. Min Act: -0.1700
Data Index: 4755497 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1164501 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.7276. Min Act: -0.1700
Data Index: 2086786 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6963. Min Act: -0.1700
Data Index: 6624832 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6651. Min Act: -0.1700
Data Index: 1550295 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6651. Min Act: -0.1700
Data Index: 5138608 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6963. Min Act: -0.1700
Data Index: 5019439 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6026. Min Act: -0.1700
Data Index: 3002812 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6338. Min Act: -0.1700
Data Index: 5665387 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6026. Min Act: -0.1700
Data Index: 435993 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6338. Min Act: -0.1700
Data Index: 4022588 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0401. Min Range: -6.0401
Max Act: 5.6338. Min Act: -0.1700
Data Index: 1337299 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19