Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.7201. Min Act: -0.1700
Data Index: 882563 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.7201. Min Act: -0.1700
Data Index: 799765 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6881. Min Act: -0.1700
Data Index: 1068090 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6881. Min Act: -0.1700
Data Index: 397284 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6721. Min Act: -0.1700
Data Index: 275162 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6721. Min Act: -0.1700
Data Index: 269703 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6721. Min Act: -0.1700
Data Index: 1285553 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 861680 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 310567 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 293660 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 1203414 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 124747 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6240. Min Act: -0.1700
Data Index: 1078875 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6400. Min Act: -0.1700
Data Index: 340515 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6400. Min Act: -0.1700
Data Index: 719479 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6400. Min Act: -0.1700
Data Index: 486776 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6400. Min Act: -0.1700
Data Index: 187826 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6561. Min Act: -0.1700
Data Index: 385144 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6240. Min Act: -0.1700
Data Index: 741083 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7201. Min Range: -2.7201
Max Act: 2.6240. Min Act: -0.1700
Data Index: 37243 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19