Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 255 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0071. Min Range: -3.0071
Max Act: 3.0071. Min Act: -0.1700
Data Index: 573536 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0071. Min Range: -3.0071
Max Act: 3.0071. Min Act: -0.1700
Data Index: 4568 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0071. Min Range: -3.0071
Max Act: 3.0071. Min Act: -0.1700
Data Index: 357655 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0071. Min Range: -3.0071
Max Act: 3.0071. Min Act: -0.1700
Data Index: 808353 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9913. Min Act: -0.1700
Data Index: 1073341 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9913. Min Act: -0.1700
Data Index: 1316278 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9754. Min Act: -0.1700
Data Index: 264393 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9913. Min Act: -0.1700
Data Index: 365864 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9913. Min Act: -0.1700
Data Index: 159211 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9754. Min Act: -0.1700
Data Index: 289922 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9754. Min Act: -0.1700
Data Index: 1183666 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9913. Min Act: -0.1700
Data Index: 565603 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 605114 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 17767 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 74428 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 994061 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9754. Min Act: -0.1700
Data Index: 183370 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 356633 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9754. Min Act: -0.1700
Data Index: 1230020 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0071. Min Range: -3.0071
Max Act: 2.9596. Min Act: -0.1700
Data Index: 531132 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19