Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1634 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.7089. Min Act: -0.1700
Data Index: 1035254 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.7089. Min Act: -0.1700
Data Index: 984524 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6929. Min Act: -0.1700
Data Index: 431764 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6609. Min Act: -0.1700
Data Index: 777942 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6609. Min Act: -0.1700
Data Index: 193762 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6449. Min Act: -0.1700
Data Index: 2514 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6609. Min Act: -0.1700
Data Index: 93548 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6769. Min Act: -0.1700
Data Index: 327623 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6449. Min Act: -0.1700
Data Index: 101780 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6449. Min Act: -0.1700
Data Index: 1308343 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6449. Min Act: -0.1700
Data Index: 408901 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6288. Min Act: -0.1700
Data Index: 1164824 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6288. Min Act: -0.1700
Data Index: 132274 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6288. Min Act: -0.1700
Data Index: 593609 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6127. Min Act: -0.1700
Data Index: 33408 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6127. Min Act: -0.1700
Data Index: 155947 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6127. Min Act: -0.1700
Data Index: 677461 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6127. Min Act: -0.1700
Data Index: 220371 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.5966. Min Act: -0.1700
Data Index: 417822 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7089. Min Range: -2.7089
Max Act: 2.6127. Min Act: -0.1700
Data Index: 188508 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19