Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4984. Min Act: -0.1700
Data Index: 532878 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4359. Min Act: -0.1700
Data Index: 400440 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3109. Min Act: -0.1700
Data Index: 714652 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3109. Min Act: -0.1700
Data Index: 478748 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3109. Min Act: -0.1700
Data Index: 1197162 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1859. Min Act: -0.1700
Data Index: 956523 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.2484. Min Act: -0.1700
Data Index: 1154133 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.2484. Min Act: -0.1700
Data Index: 842035 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1859. Min Act: -0.1700
Data Index: 834558 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1234. Min Act: -0.1700
Data Index: 1294802 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.0921. Min Act: -0.1700
Data Index: 1351626 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1546. Min Act: -0.1700
Data Index: 883997 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1546. Min Act: -0.1700
Data Index: 166742 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.2171. Min Act: -0.1700
Data Index: 1138407 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.2484. Min Act: -0.1700
Data Index: 143007 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1859. Min Act: -0.1700
Data Index: 836294 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1234. Min Act: -0.1700
Data Index: 960368 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1087779 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1859. Min Act: -0.1700
Data Index: 374468 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.0921. Min Act: -0.1700
Data Index: 1293923 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19