Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 185 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 10.1219. Min Range: -10.1219
Max Act: 10.1219. Min Act: -0.1700
Data Index: 91406 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1219. Min Range: -10.1219
Max Act: 10.0594. Min Act: -0.1699
Data Index: 225389 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1219. Min Range: -10.1219
Max Act: 10.0594. Min Act: -0.1697
Data Index: 301865 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 29429 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 477840 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9344. Min Act: -0.1696
Data Index: 341956 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1219. Min Range: -10.1219
Max Act: 10.0594. Min Act: -0.1700
Data Index: 494835 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1219. Min Range: -10.1219
Max Act: 10.0594. Min Act: -0.1699
Data Index: 1073940 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 1197179 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 1223778 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1696
Data Index: 1234277 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 406931 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1699
Data Index: 419429 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1699
Data Index: 301747 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1700
Data Index: 444620 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9969. Min Act: -0.1699
Data Index: 670857 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.8719. Min Act: -0.1699
Data Index: 681740 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9344. Min Act: -0.1700
Data Index: 213803 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9344. Min Act: -0.1699
Data Index: 727271 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1219. Min Range: -10.1219
Max Act: 9.9344. Min Act: -0.1696
Data Index: 758021 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19