Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1925 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.2878. Min Act: -0.1700
Data Index: 333139 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.2253. Min Act: -0.1700
Data Index: 470079 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.2253. Min Act: -0.1700
Data Index: 1203463 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.2566. Min Act: -0.1700
Data Index: 109005 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1941. Min Act: -0.1700
Data Index: 78073 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1628. Min Act: -0.1700
Data Index: 688800 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1315. Min Act: -0.1700
Data Index: 772747 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1628. Min Act: -0.1700
Data Index: 45601 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1332609 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 512850 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 196228 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 636342 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1003. Min Act: -0.1700
Data Index: 772900 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1003. Min Act: -0.1700
Data Index: 1252820 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1628. Min Act: -0.1699
Data Index: 1084654 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 188739 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1003. Min Act: -0.1700
Data Index: 709759 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 1049604 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.1003. Min Act: -0.1700
Data Index: 665517 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2878. Min Range: -4.2878
Max Act: 4.0690. Min Act: -0.1700
Data Index: 1113815 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19