Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1817 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.9019. Min Act: -0.1700
Data Index: 1077700 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.9644. Min Act: -0.1700
Data Index: 1030313 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.9019. Min Act: -0.1699
Data Index: 785853 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8394. Min Act: -0.1700
Data Index: 1271321 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8706. Min Act: -0.1700
Data Index: 487659 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8394. Min Act: -0.1700
Data Index: 89144 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.9331. Min Act: -0.1700
Data Index: 1128282 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8394. Min Act: -0.1700
Data Index: 399605 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8394. Min Act: -0.1700
Data Index: 558913 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8081. Min Act: -0.1700
Data Index: 26028 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8394. Min Act: -0.1700
Data Index: 1178931 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8706. Min Act: -0.1700
Data Index: 1200223 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8081. Min Act: -0.1700
Data Index: 1221445 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.8081. Min Act: -0.1700
Data Index: 817917 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.7456. Min Act: -0.1700
Data Index: 93006 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.7456. Min Act: -0.1700
Data Index: 156980 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.7456. Min Act: -0.1700
Data Index: 481572 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.7769. Min Act: -0.1700
Data Index: 574176 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.7456. Min Act: -0.1700
Data Index: 1052432 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9644. Min Range: -4.9644
Max Act: 4.6831. Min Act: -0.1699
Data Index: 913396 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19