Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1866 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6332. Min Act: -0.1700
Data Index: 1036182 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6493. Min Act: -0.1700
Data Index: 1129483 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6332. Min Act: -0.1700
Data Index: 486781 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6493. Min Act: -0.1700
Data Index: 247975 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6332. Min Act: -0.1700
Data Index: 433631 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5688. Min Act: -0.1700
Data Index: 1147579 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6332. Min Act: -0.1700
Data Index: 1220144 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6171. Min Act: -0.1700
Data Index: 613353 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5850. Min Act: -0.1700
Data Index: 487845 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5688. Min Act: -0.1700
Data Index: 1072840 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5688. Min Act: -0.1700
Data Index: 858126 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.6011. Min Act: -0.1700
Data Index: 692800 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5366. Min Act: -0.1700
Data Index: 1258887 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5527. Min Act: -0.1700
Data Index: 595378 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5688. Min Act: -0.1700
Data Index: 359663 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5688. Min Act: -0.1700
Data Index: 78021 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5366. Min Act: -0.1700
Data Index: 599816 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.4880. Min Act: -0.1700
Data Index: 1127109 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.5204. Min Act: -0.1700
Data Index: 1579650 (Python Code)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6493. Min Range: -2.6493
Max Act: 2.4880. Min Act: -0.1700
Data Index: 1148411 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19