Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 998 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.7264. Min Act: -0.1700
Data Index: 561131 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.6303. Min Act: -0.1700
Data Index: 913715 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.6303. Min Act: -0.1700
Data Index: 792216 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.6142. Min Act: -0.1700
Data Index: 873908 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5981. Min Act: -0.1700
Data Index: 211287 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5981. Min Act: -0.1700
Data Index: 173235 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5981. Min Act: -0.1700
Data Index: 1114730 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5981. Min Act: -0.1700
Data Index: 472155 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5820. Min Act: -0.1700
Data Index: 1167724 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5820. Min Act: -0.1700
Data Index: 1227403 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5820. Min Act: -0.1700
Data Index: 872978 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 1145324 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5820. Min Act: -0.1700
Data Index: 398104 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 1171683 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5498. Min Act: -0.1700
Data Index: 820775 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 834127 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 667330 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 243823 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5659. Min Act: -0.1700
Data Index: 272817 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7264. Min Range: -2.7264
Max Act: 2.5498. Min Act: -0.1700
Data Index: 1113329 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19