Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1798 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.7026. Min Act: -0.1700
Data Index: 285779 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6706. Min Act: -0.1700
Data Index: 744306 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6706. Min Act: -0.1700
Data Index: 1069852 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.7026. Min Act: -0.1700
Data Index: 590813 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6385. Min Act: -0.1700
Data Index: 1039243 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6546. Min Act: -0.1700
Data Index: 781785 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6546. Min Act: -0.1700
Data Index: 1266047 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6385. Min Act: -0.1700
Data Index: 994034 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6385. Min Act: -0.1700
Data Index: 498216 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.6225. Min Act: -0.1700
Data Index: 891512 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5903. Min Act: -0.1700
Data Index: 419267 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5903. Min Act: -0.1700
Data Index: 179796 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5742. Min Act: -0.1700
Data Index: 1060229 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5742. Min Act: -0.1700
Data Index: 240321 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5581. Min Act: -0.1700
Data Index: 550127 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5581. Min Act: -0.1700
Data Index: 561577 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5258. Min Act: -0.1700
Data Index: 84349 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5258. Min Act: -0.1700
Data Index: 1250577 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.5096. Min Act: -0.1700
Data Index: 587009 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7026. Min Range: -2.7026
Max Act: 2.4934. Min Act: -0.1700
Data Index: 1260917 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19