Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 13 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.2109. Min Act: -0.1700
Data Index: 1199617 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.1171. Min Act: -0.1700
Data Index: 1126172 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.1796. Min Act: -0.1700
Data Index: 700002 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.1171. Min Act: -0.1700
Data Index: 836746 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.1171. Min Act: -0.1700
Data Index: 74284 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0546. Min Act: -0.1700
Data Index: 261683 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0233. Min Act: -0.1700
Data Index: 272304 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0546. Min Act: -0.1700
Data Index: 152125 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9608. Min Act: -0.1700
Data Index: 91465 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9920. Min Act: -0.1700
Data Index: 481842 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0546. Min Act: -0.1700
Data Index: 939256 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0546. Min Act: -0.1700
Data Index: 1010833 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9920. Min Act: -0.1700
Data Index: 778682 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0233. Min Act: -0.1700
Data Index: 926795 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9608. Min Act: -0.1700
Data Index: 937067 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9920. Min Act: -0.1700
Data Index: 316234 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9920. Min Act: -0.1700
Data Index: 870469 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9920. Min Act: -0.1700
Data Index: 557888 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2109. Min Range: -4.2109
Max Act: 3.9295. Min Act: -0.1700
Data Index: 1105085 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2109. Min Range: -4.2109
Max Act: 4.0233. Min Act: -0.1700
Data Index: 320047 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19