Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 664 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.2020. Min Range: -3.2020
Max Act: 3.2020. Min Act: -0.1700
Data Index: 1307041 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2020. Min Range: -3.2020
Max Act: 3.1390. Min Act: -0.1700
Data Index: 27078 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2020. Min Range: -3.2020
Max Act: 3.0917. Min Act: -0.1700
Data Index: 1060140 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2020. Min Range: -3.2020
Max Act: 3.0602. Min Act: -0.1700
Data Index: 1250252 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2020. Min Range: -3.2020
Max Act: 3.0128. Min Act: -0.1700
Data Index: 398165 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9812. Min Act: -0.1700
Data Index: 365477 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9020. Min Act: -0.1700
Data Index: 1323269 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9178. Min Act: -0.1700
Data Index: 1324332 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9178. Min Act: -0.1700
Data Index: 387514 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9495. Min Act: -0.1700
Data Index: 1079723 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9020. Min Act: -0.1700
Data Index: 414904 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.9020. Min Act: -0.1700
Data Index: 1351981 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8544. Min Act: -0.1700
Data Index: 1198018 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8544. Min Act: -0.1700
Data Index: 674067 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8544. Min Act: -0.1700
Data Index: 302019 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8544. Min Act: -0.1700
Data Index: 1187124 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8861. Min Act: -0.1700
Data Index: 1244174 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8226. Min Act: -0.1700
Data Index: 6820 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.7907. Min Act: -0.1700
Data Index: 507367 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2020. Min Range: -3.2020
Max Act: 2.8544. Min Act: -0.1700
Data Index: 653837 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19