Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 240 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.2831. Min Act: -0.1700
Data Index: 547111 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.2518. Min Act: -0.1700
Data Index: 375973 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0955. Min Act: -0.1700
Data Index: 614816 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1268. Min Act: -0.1700
Data Index: 745686 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1038326 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1893. Min Act: -0.1700
Data Index: 429414 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1075911 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1581. Min Act: -0.1700
Data Index: 497464 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0955. Min Act: -0.1700
Data Index: 226145 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0330. Min Act: -0.1700
Data Index: 533859 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.1893. Min Act: -0.1700
Data Index: 41446 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0487. Min Act: -0.1700
Data Index: 285213 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0330. Min Act: -0.1700
Data Index: 162408 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2831. Min Range: -4.2831
Max Act: 3.9705. Min Act: -0.1700
Data Index: 28935 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2831. Min Range: -4.2831
Max Act: 3.9705. Min Act: -0.1700
Data Index: 892575 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0018. Min Act: -0.1700
Data Index: 940889 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0643. Min Act: -0.1700
Data Index: 749436 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0955. Min Act: -0.1700
Data Index: 679042 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2831. Min Range: -4.2831
Max Act: 4.0643. Min Act: -0.1700
Data Index: 657941 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2831. Min Range: -4.2831
Max Act: 3.9236. Min Act: -0.1700
Data Index: 794042 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19