Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 137 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.8157. Min Act: -0.1700
Data Index: 982148 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7845. Min Act: -0.1700
Data Index: 890331 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7532. Min Act: -0.1700
Data Index: 942383 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7845. Min Act: -0.1700
Data Index: 1316723 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7532. Min Act: -0.1700
Data Index: 330088 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7532. Min Act: -0.1700
Data Index: 1037736 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7219. Min Act: -0.1700
Data Index: 956083 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7845. Min Act: -0.1700
Data Index: 533121 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7219. Min Act: -0.1700
Data Index: 1068173 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7219. Min Act: -0.1700
Data Index: 227584 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7532. Min Act: -0.1700
Data Index: 43456 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.7219. Min Act: -0.1700
Data Index: 233797 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6594. Min Act: -0.1700
Data Index: 1280671 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6907. Min Act: -0.1700
Data Index: 432443 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6907. Min Act: -0.1700
Data Index: 1012721 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6282. Min Act: -0.1700
Data Index: 1250469 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6594. Min Act: -0.1700
Data Index: 1047092 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6594. Min Act: -0.1700
Data Index: 781639 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6282. Min Act: -0.1700
Data Index: 150144 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8157. Min Range: -4.8157
Max Act: 4.6282. Min Act: -0.1700
Data Index: 386649 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19