Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 19 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0773. Min Range: -5.0773
Max Act: 5.0773. Min Act: -0.1700
Data Index: 400203 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0773. Min Range: -5.0773
Max Act: 5.0773. Min Act: -0.1700
Data Index: 1042137 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.8585. Min Act: -0.1700
Data Index: 748996 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.8273. Min Act: -0.1700
Data Index: 957869 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.8898. Min Act: -0.1700
Data Index: 168636 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.8273. Min Act: -0.1700
Data Index: 493997 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7648. Min Act: -0.1700
Data Index: 1289642 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7335. Min Act: -0.1700
Data Index: 596817 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7335. Min Act: -0.1700
Data Index: 976456 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7648. Min Act: -0.1700
Data Index: 447015 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7023. Min Act: -0.1700
Data Index: 105709 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.7023. Min Act: -0.1700
Data Index: 9 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6398. Min Act: -0.1700
Data Index: 1036374 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6710. Min Act: -0.1700
Data Index: 215836 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.5773. Min Act: -0.1700
Data Index: 315389 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6085. Min Act: -0.1700
Data Index: 400558 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6085. Min Act: -0.1700
Data Index: 539992 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6398. Min Act: -0.1700
Data Index: 60938 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6085. Min Act: -0.1700
Data Index: 991599 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0773. Min Range: -5.0773
Max Act: 4.6085. Min Act: -0.1700
Data Index: 740328 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19