Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1927 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.3891. Min Act: -0.1700
Data Index: 970299 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2953. Min Act: -0.1700
Data Index: 869985 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2953. Min Act: -0.1700
Data Index: 1341627 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2953. Min Act: -0.1700
Data Index: 798015 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2328. Min Act: -0.1700
Data Index: 1153613 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2641. Min Act: -0.1700
Data Index: 1163700 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2328. Min Act: -0.1700
Data Index: 792202 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2016. Min Act: -0.1700
Data Index: 833839 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2328. Min Act: -0.1700
Data Index: 154655 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2016. Min Act: -0.1700
Data Index: 1064440 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1703. Min Act: -0.1700
Data Index: 524242 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1390. Min Act: -0.1700
Data Index: 937118 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2328. Min Act: -0.1700
Data Index: 373981 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1703. Min Act: -0.1700
Data Index: 26684 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2016. Min Act: -0.1700
Data Index: 1352496 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1703. Min Act: -0.1700
Data Index: 856980 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2016. Min Act: -0.1700
Data Index: 768670 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1390. Min Act: -0.1700
Data Index: 1001876 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.1390. Min Act: -0.1700
Data Index: 571039 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3891. Min Range: -4.3891
Max Act: 4.2016. Min Act: -0.1700
Data Index: 1066003 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19