Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0495. Min Range: -7.0495
Max Act: 7.0495. Min Act: -0.1700
Data Index: 4919994 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0495. Min Range: -7.0495
Max Act: 7.0495. Min Act: -0.1700
Data Index: 6283763 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9245. Min Act: -0.1700
Data Index: 6971482 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9870. Min Act: -0.1700
Data Index: 7290039 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9870. Min Act: -0.1700
Data Index: 7502741 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9870. Min Act: -0.1700
Data Index: 2219877 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9245. Min Act: -0.1700
Data Index: 2359750 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1700
Data Index: 667262 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8620. Min Act: -0.1698
Data Index: 1860316 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.9245. Min Act: -0.1700
Data Index: 7621545 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8620. Min Act: -0.1700
Data Index: 6108399 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1534
Data Index: 8230263 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1700
Data Index: 50863 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1698
Data Index: 867392 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1700
Data Index: 6236257 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8620. Min Act: -0.1700
Data Index: 4455129 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8620. Min Act: -0.1700
Data Index: 5277490 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8933. Min Act: -0.1534
Data Index: 5274434 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.7995. Min Act: -0.1534
Data Index: 158690 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0495. Min Range: -7.0495
Max Act: 6.8620. Min Act: -0.1700
Data Index: 1661328 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19