Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2016 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0069. Min Range: -4.0069
Max Act: 4.0069. Min Act: -0.1700
Data Index: 246374 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0069. Min Range: -4.0069
Max Act: 4.0069. Min Act: -0.1700
Data Index: 253903 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.9443. Min Act: -0.1700
Data Index: 1203145 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.9443. Min Act: -0.1700
Data Index: 464764 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.9131. Min Act: -0.1700
Data Index: 788096 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8974. Min Act: -0.1700
Data Index: 1040988 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.9131. Min Act: -0.1700
Data Index: 584438 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8818. Min Act: -0.1700
Data Index: 259565 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8662. Min Act: -0.1700
Data Index: 792295 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8349. Min Act: -0.1700
Data Index: 1048137 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8349. Min Act: -0.1700
Data Index: 623511 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8505. Min Act: -0.1700
Data Index: 1115527 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8349. Min Act: -0.1700
Data Index: 149792 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8349. Min Act: -0.1700
Data Index: 1061574 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8036. Min Act: -0.1700
Data Index: 1290784 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8192. Min Act: -0.1700
Data Index: 41629 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8036. Min Act: -0.1700
Data Index: 1200075 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.7880. Min Act: -0.1700
Data Index: 1421658 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.8192. Min Act: -0.1700
Data Index: 688848 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0069. Min Range: -4.0069
Max Act: 3.7880. Min Act: -0.1700
Data Index: 44574 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19