Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 695 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.1655. Min Act: -0.1700
Data Index: 1002042 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.1340. Min Act: -0.1700
Data Index: 956850 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0710. Min Act: -0.1700
Data Index: 1277152 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0394. Min Act: -0.1700
Data Index: 195021 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0394. Min Act: -0.1700
Data Index: 1103877 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0078. Min Act: -0.1700
Data Index: 1268053 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0078. Min Act: -0.1700
Data Index: 1213130 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 572153 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 600154 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0236. Min Act: -0.1700
Data Index: 661683 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 344459 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0078. Min Act: -0.1700
Data Index: 987305 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0236. Min Act: -0.1700
Data Index: 608617 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 958723 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9762. Min Act: -0.1700
Data Index: 962939 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 642657 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1655. Min Range: -3.1655
Max Act: 3.0078. Min Act: -0.1700
Data Index: 1032224 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9762. Min Act: -0.1700
Data Index: 945606 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9920. Min Act: -0.1700
Data Index: 1141475 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1655. Min Range: -3.1655
Max Act: 2.9762. Min Act: -0.1700
Data Index: 590055 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19