Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 652 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7675. Min Act: -0.1700
Data Index: 1158580 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7196. Min Act: -0.1700
Data Index: 728009 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7196. Min Act: -0.1700
Data Index: 64063 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7355. Min Act: -0.1700
Data Index: 909502 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7355. Min Act: -0.1700
Data Index: 1185499 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 958927 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7196. Min Act: -0.1700
Data Index: 954710 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 233050 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 1092241 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 1589571 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 780478 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 1025494 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 302346 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.6876. Min Act: -0.1700
Data Index: 1287292 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.6876. Min Act: -0.1700
Data Index: 159403 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.6876. Min Act: -0.1700
Data Index: 1006130 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 264819 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 27511 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 644812 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7675. Min Range: -2.7675
Max Act: 2.7036. Min Act: -0.1700
Data Index: 1219769 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19