Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 35 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2569. Min Act: -0.1698
Data Index: 492598 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2569. Min Act: -0.1700
Data Index: 879393 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2569. Min Act: -0.1699
Data Index: 84299 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2239. Min Act: -0.1696
Data Index: 566977 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2239. Min Act: -0.1699
Data Index: 1221026 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2239. Min Act: -0.1700
Data Index: 591433 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2073. Min Act: -0.1699
Data Index: 286412 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.2073. Min Act: -0.1700
Data Index: 588294 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1907. Min Act: -0.1699
Data Index: 779306 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1741. Min Act: -0.1699
Data Index: 192839 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1741. Min Act: -0.1700
Data Index: 952137 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1741. Min Act: -0.1700
Data Index: 1002021 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1741. Min Act: -0.1700
Data Index: 915068 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1699
Data Index: 794400 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1408. Min Act: -0.1699
Data Index: 796902 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1700
Data Index: 420537 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1699
Data Index: 109407 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1700
Data Index: 240048 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1700
Data Index: 294040 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2569. Min Range: -2.2569
Max Act: 2.1575. Min Act: -0.1700
Data Index: 12473 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19