Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1294 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.6999. Min Act: -0.1700
Data Index: 116340 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.6518. Min Act: -0.1700
Data Index: 579912 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5875. Min Act: -0.1700
Data Index: 673992 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.6036. Min Act: -0.1700
Data Index: 779941 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5875. Min Act: -0.1700
Data Index: 1120898 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5714. Min Act: -0.1700
Data Index: 975231 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5714. Min Act: -0.1700
Data Index: 66766 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5714. Min Act: -0.1700
Data Index: 155575 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5553. Min Act: -0.1700
Data Index: 625404 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5553. Min Act: -0.1700
Data Index: 735763 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5068. Min Act: -0.1700
Data Index: 602 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5230. Min Act: -0.1700
Data Index: 473001 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5230. Min Act: -0.1700
Data Index: 579113 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5553. Min Act: -0.1700
Data Index: 360835 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5230. Min Act: -0.1700
Data Index: 352137 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5230. Min Act: -0.1700
Data Index: 204513 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5068. Min Act: -0.1700
Data Index: 55478 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5068. Min Act: -0.1700
Data Index: 622927 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5391. Min Act: -0.1700
Data Index: 723074 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6999. Min Range: -2.6999
Max Act: 2.5068. Min Act: -0.1700
Data Index: 415159 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19