Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1659 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.8753. Min Act: -0.1700
Data Index: 545521 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.8127. Min Act: -0.1700
Data Index: 913396 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.8440. Min Act: -0.1700
Data Index: 419086 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.8440. Min Act: -0.1700
Data Index: 507125 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.8127. Min Act: -0.1700
Data Index: 1309247 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.7501. Min Act: -0.1700
Data Index: 921989 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.7188. Min Act: -0.1700
Data Index: 831638 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.7188. Min Act: -0.1700
Data Index: 725960 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.7188. Min Act: -0.1700
Data Index: 558732 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.7188. Min Act: -0.1700
Data Index: 165378 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6562. Min Act: -0.1700
Data Index: 1112012 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6875. Min Act: -0.1700
Data Index: 914368 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6875. Min Act: -0.1700
Data Index: 1038921 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6562. Min Act: -0.1700
Data Index: 255205 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6562. Min Act: -0.1700
Data Index: 1296393 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6562. Min Act: -0.1700
Data Index: 241713 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6249. Min Act: -0.1700
Data Index: 531135 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6875. Min Act: -0.1700
Data Index: 571424 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6249. Min Act: -0.1700
Data Index: 4883 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8753. Min Range: -3.8753
Max Act: 3.6562. Min Act: -0.1700
Data Index: 1077553 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19