Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.3180. Min Range: -10.3180
Max Act: 10.3180. Min Act: -0.1700
Data Index: 7419105 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3180. Min Range: -10.3180
Max Act: 10.0680. Min Act: -0.1700
Data Index: 385312 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.9430. Min Act: -0.1700
Data Index: 7818232 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.9430. Min Act: -0.1700
Data Index: 7818217 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.9430. Min Act: -0.1700
Data Index: 2321407 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8180. Min Act: -0.1700
Data Index: 4247554 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8805. Min Act: -0.1700
Data Index: 4313553 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8180. Min Act: -0.1700
Data Index: 7419122 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8180. Min Act: -0.1700
Data Index: 7778802 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8180. Min Act: -0.1700
Data Index: 4313568 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.7555. Min Act: -0.1700
Data Index: 4244711 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6930. Min Act: -0.1700
Data Index: 1847941 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6930. Min Act: -0.1700
Data Index: 4247567 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.8180. Min Act: -0.1700
Data Index: 8640630 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6930. Min Act: -0.1700
Data Index: 8697669 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6930. Min Act: -0.1700
Data Index: 7839764 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.5680. Min Act: -0.1700
Data Index: 4244709 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6305. Min Act: -0.1700
Data Index: 6709737 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6305. Min Act: -0.1700
Data Index: 4247555 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3180. Min Range: -10.3180
Max Act: 9.6305. Min Act: -0.1700
Data Index: 1827251 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19