Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1165 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.7502. Min Act: -0.1694
Data Index: 726199 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.7342. Min Act: -0.1700
Data Index: 226977 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.7022. Min Act: -0.1700
Data Index: 1321995 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6862. Min Act: -0.1700
Data Index: 532015 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6862. Min Act: -0.1700
Data Index: 665361 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6862. Min Act: -0.1700
Data Index: 348443 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6862. Min Act: -0.1700
Data Index: 259302 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6702. Min Act: -0.1700
Data Index: 781418 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6702. Min Act: -0.1700
Data Index: 748249 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6702. Min Act: -0.1700
Data Index: 157238 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6542. Min Act: -0.1700
Data Index: 561430 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6542. Min Act: -0.1700
Data Index: 871412 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6381. Min Act: -0.1700
Data Index: 1007385 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6220. Min Act: -0.1700
Data Index: 445542 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6381. Min Act: -0.1700
Data Index: 666410 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6542. Min Act: -0.1700
Data Index: 1206044 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6542. Min Act: -0.1691
Data Index: 86086 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6220. Min Act: -0.1700
Data Index: 225518 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6220. Min Act: -0.1700
Data Index: 56885 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7502. Min Range: -2.7502
Max Act: 2.6060. Min Act: -0.1700
Data Index: 424698 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19