Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 64 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.4734. Min Act: -0.1700
Data Index: 683598 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.4421. Min Act: -0.1700
Data Index: 1147702 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3796. Min Act: -0.1700
Data Index: 790783 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.4421. Min Act: -0.1700
Data Index: 1161687 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3484. Min Act: -0.1700
Data Index: 627804 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3796. Min Act: -0.1700
Data Index: 1148302 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3484. Min Act: -0.1700
Data Index: 36992 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.4109. Min Act: -0.1700
Data Index: 760222 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3484. Min Act: -0.1700
Data Index: 899850 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 882381 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 12813 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 40902 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3484. Min Act: -0.1700
Data Index: 932305 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 66212 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 32889 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.2858. Min Act: -0.1700
Data Index: 974284 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.2858. Min Act: -0.1700
Data Index: 27563 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 1074254 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.3171. Min Act: -0.1700
Data Index: 494786 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4734. Min Range: -4.4734
Max Act: 4.2858. Min Act: -0.1700
Data Index: 259177 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19