Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 280 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.0393. Min Range: -6.0393
Max Act: 6.0393. Min Act: -0.1700
Data Index: 11845 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0393. Min Range: -6.0393
Max Act: 6.0081. Min Act: -0.1700
Data Index: 828777 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8831. Min Act: -0.1700
Data Index: 1070715 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 934806 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 1020980 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 293212 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8831. Min Act: -0.1700
Data Index: 454337 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 753814 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8831. Min Act: -0.1700
Data Index: 719867 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 134415 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8831. Min Act: -0.1700
Data Index: 719802 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 785122 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 554903 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 618010 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.7893. Min Act: -0.1700
Data Index: 402077 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 663046 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 411533 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 686724 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8206. Min Act: -0.1700
Data Index: 243565 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0393. Min Range: -6.0393
Max Act: 5.8518. Min Act: -0.1700
Data Index: 454 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19