Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 78 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.7524. Min Act: -0.1700
Data Index: 1188979 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.7205. Min Act: -0.1700
Data Index: 778472 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.7045. Min Act: -0.1700
Data Index: 873477 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6885. Min Act: -0.1700
Data Index: 53512 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6724. Min Act: -0.1700
Data Index: 637543 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6564. Min Act: -0.1700
Data Index: 1222961 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6404. Min Act: -0.1700
Data Index: 612541 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6564. Min Act: -0.1700
Data Index: 372366 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6564. Min Act: -0.1700
Data Index: 1342952 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6724. Min Act: -0.1700
Data Index: 102149 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6564. Min Act: -0.1700
Data Index: 1132724 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6564. Min Act: -0.1700
Data Index: 724573 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6404. Min Act: -0.1700
Data Index: 460137 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6404. Min Act: -0.1700
Data Index: 265114 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6404. Min Act: -0.1700
Data Index: 186125 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6243. Min Act: -0.1700
Data Index: 665027 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6404. Min Act: -0.1700
Data Index: 360792 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6243. Min Act: -0.1700
Data Index: 767253 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6243. Min Act: -0.1700
Data Index: 1569450 (Python Code)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7524. Min Range: -2.7524
Max Act: 2.6243. Min Act: -0.1700
Data Index: 847350 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19