Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 655 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.5063. Min Act: -0.1700
Data Index: 417878 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.5063. Min Act: -0.1700
Data Index: 919188 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.4750. Min Act: -0.1700
Data Index: 684498 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.4750. Min Act: -0.1700
Data Index: 741421 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.4125. Min Act: -0.1700
Data Index: 1063265 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 1325777 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3188. Min Act: -0.1700
Data Index: 879628 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 536201 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.4125. Min Act: -0.1700
Data Index: 297641 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 146223 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 522151 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 379116 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3188. Min Act: -0.1700
Data Index: 412957 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 539046 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3188. Min Act: -0.1700
Data Index: 206410 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.2563. Min Act: -0.1700
Data Index: 698009 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 49396 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 1035245 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.2875. Min Act: -0.1700
Data Index: 746116 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5063. Min Range: -6.5063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 1087985 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19