Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 640 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0779. Min Range: -3.0779
Max Act: 3.0779. Min Act: -0.1700
Data Index: 162298 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0779. Min Range: -3.0779
Max Act: 3.0779. Min Act: -0.1700
Data Index: 926920 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0779. Min Range: -3.0779
Max Act: 3.0305. Min Act: -0.1700
Data Index: 1112862 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0779. Min Range: -3.0779
Max Act: 3.0305. Min Act: -0.1700
Data Index: 487896 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9989. Min Act: -0.1700
Data Index: 1024909 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9989. Min Act: -0.1699
Data Index: 57775 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9831. Min Act: -0.1700
Data Index: 329819 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9831. Min Act: -0.1700
Data Index: 18491 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9831. Min Act: -0.1700
Data Index: 255250 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9831. Min Act: -0.1700
Data Index: 837300 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9831. Min Act: -0.1700
Data Index: 1173083 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9673. Min Act: -0.1700
Data Index: 39226 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9515. Min Act: -0.1700
Data Index: 65946 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9673. Min Act: -0.1700
Data Index: 222725 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9673. Min Act: -0.1700
Data Index: 932773 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9673. Min Act: -0.1700
Data Index: 595159 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9515. Min Act: -0.1700
Data Index: 792697 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9356. Min Act: -0.1700
Data Index: 188794 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9673. Min Act: -0.1700
Data Index: 841022 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0779. Min Range: -3.0779
Max Act: 2.9515. Min Act: -0.1700
Data Index: 355105 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19