Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.8026. Min Act: -0.1700
Data Index: 2968303 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.7401. Min Act: -0.1700
Data Index: 1185039 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.7401. Min Act: -0.1700
Data Index: 4055969 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.6932. Min Act: -0.1700
Data Index: 403669 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.6775. Min Act: -0.1700
Data Index: 8415427 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.6619. Min Act: -0.1700
Data Index: 3070271 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5836. Min Act: -0.1700
Data Index: 7294256 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.6306. Min Act: -0.1700
Data Index: 258893 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.6306. Min Act: -0.1700
Data Index: 7733610 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5993. Min Act: -0.1700
Data Index: 6615922 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5993. Min Act: -0.1700
Data Index: 1185042 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5836. Min Act: -0.1700
Data Index: 708586 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5993. Min Act: -0.1700
Data Index: 82747 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5993. Min Act: -0.1700
Data Index: 4235991 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5680. Min Act: -0.1700
Data Index: 7349978 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5680. Min Act: -0.1700
Data Index: 1185040 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5523. Min Act: -0.1700
Data Index: 6041646 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5523. Min Act: -0.1700
Data Index: 918509 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5210. Min Act: -0.1700
Data Index: 1999073 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8026. Min Range: -3.8026
Max Act: 3.5367. Min Act: -0.1700
Data Index: 473054 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19