Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.2043. Min Act: -0.1700
Data Index: 4433961 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1711. Min Act: -0.1700
Data Index: 847938 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1544. Min Act: -0.1700
Data Index: 1018954 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1711. Min Act: -0.1700
Data Index: 7995780 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1377. Min Act: -0.1700
Data Index: 941518 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1377. Min Act: -0.1700
Data Index: 1926182 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1377. Min Act: -0.1700
Data Index: 6953990 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1210. Min Act: -0.1700
Data Index: 6516844 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1210. Min Act: -0.1700
Data Index: 4419962 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1210. Min Act: -0.1700
Data Index: 7590959 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1043. Min Act: -0.1700
Data Index: 7275035 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1043. Min Act: -0.1700
Data Index: 2119429 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.1043. Min Act: -0.1700
Data Index: 7096241 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0708. Min Act: -0.1700
Data Index: 4988566 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0708. Min Act: -0.1700
Data Index: 2773670 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0875. Min Act: -0.1700
Data Index: 2264810 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0708. Min Act: -0.1700
Data Index: 4881659 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0540. Min Act: -0.1700
Data Index: 7885177 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0540. Min Act: -0.1700
Data Index: 791697 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2043. Min Range: -2.2043
Max Act: 2.0540. Min Act: -0.1700
Data Index: 6268105 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19