Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 95 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.7216. Min Act: -0.1700
Data Index: 78071 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.7216. Min Act: -0.1700
Data Index: 551896 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.7056. Min Act: -0.1700
Data Index: 1170284 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.7056. Min Act: -0.1700
Data Index: 420749 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.7056. Min Act: -0.1700
Data Index: 688165 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6896. Min Act: -0.1700
Data Index: 206703 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6896. Min Act: -0.1700
Data Index: 347520 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 407540 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6576. Min Act: -0.1700
Data Index: 557865 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 865660 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 991391 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 1049085 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 1199175 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6736. Min Act: -0.1700
Data Index: 1213978 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6576. Min Act: -0.1700
Data Index: 1320094 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6896. Min Act: -0.1700
Data Index: 323806 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6576. Min Act: -0.1700
Data Index: 750684 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6576. Min Act: -0.1700
Data Index: 137727 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.6576. Min Act: -0.1700
Data Index: 396687 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7216. Min Range: -2.7216
Max Act: 2.5772. Min Act: -0.1700
Data Index: 436739 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19