Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5955. Min Range: -7.5955
Max Act: 7.5955. Min Act: -0.1700
Data Index: 5994194 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5955. Min Range: -7.5955
Max Act: 7.5017. Min Act: -0.1700
Data Index: 6406555 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5955. Min Range: -7.5955
Max Act: 7.1892. Min Act: -0.1700
Data Index: 1959702 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5955. Min Range: -7.5955
Max Act: 7.2205. Min Act: -0.1700
Data Index: 178496 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.9080. Min Act: -0.1700
Data Index: 2950170 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.8455. Min Act: -0.1700
Data Index: 5949255 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.8455. Min Act: -0.1700
Data Index: 1257594 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.7205. Min Act: -0.1700
Data Index: 7511632 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.7205. Min Act: -0.1700
Data Index: 6050043 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.6267. Min Act: -0.1700
Data Index: 4143558 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.5955. Min Act: -0.1700
Data Index: 966500 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.5955. Min Act: -0.1700
Data Index: 8339568 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.5642. Min Act: -0.1700
Data Index: 4450228 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.5330. Min Act: -0.1700
Data Index: 7077061 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4705. Min Act: -0.1700
Data Index: 1333471 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4392. Min Act: -0.1700
Data Index: 286666 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4705. Min Act: -0.1700
Data Index: 1461145 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4392. Min Act: -0.1700
Data Index: 4905448 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4392. Min Act: -0.1700
Data Index: 1987412 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5955. Min Range: -7.5955
Max Act: 6.4080. Min Act: -0.1700
Data Index: 5495814 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19