Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 165 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.9490. Min Act: -0.1700
Data Index: 451467 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.7303. Min Act: -0.1700
Data Index: 419388 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.6678. Min Act: -0.1700
Data Index: 470475 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.6678. Min Act: -0.1700
Data Index: 341118 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.6365. Min Act: -0.1700
Data Index: 391960 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 89852 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1160059 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1328183 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5428. Min Act: -0.1700
Data Index: 358175 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4490. Min Act: -0.1700
Data Index: 779591 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4803. Min Act: -0.1700
Data Index: 848127 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5428. Min Act: -0.1700
Data Index: 496201 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 456560 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4490. Min Act: -0.1700
Data Index: 325991 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4490. Min Act: -0.1700
Data Index: 56866 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4178. Min Act: -0.1700
Data Index: 692226 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4803. Min Act: -0.1700
Data Index: 470447 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1268119 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.4178. Min Act: -0.1700
Data Index: 252078 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9490. Min Range: -6.9490
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1330343 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19