Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 543 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0911. Min Range: -5.0911
Max Act: 5.0911. Min Act: -0.1700
Data Index: 387021 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0911. Min Range: -5.0911
Max Act: 5.0911. Min Act: -0.1699
Data Index: 1267713 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0911. Min Range: -5.0911
Max Act: 5.0286. Min Act: -0.1700
Data Index: 835565 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9974. Min Act: -0.1700
Data Index: 664314 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9349. Min Act: -0.1700
Data Index: 998930 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9349. Min Act: -0.1700
Data Index: 1280128 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9661. Min Act: -0.1700
Data Index: 1155789 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9036. Min Act: -0.1700
Data Index: 857547 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9036. Min Act: -0.1700
Data Index: 142901 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8411. Min Act: -0.1700
Data Index: 691159 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8411. Min Act: -0.1700
Data Index: 150413 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.9036. Min Act: -0.1700
Data Index: 146817 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8724. Min Act: -0.1700
Data Index: 1261368 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8411. Min Act: -0.1700
Data Index: 1330590 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8724. Min Act: -0.1700
Data Index: 265049 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8724. Min Act: -0.1700
Data Index: 1092467 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8411. Min Act: -0.1700
Data Index: 1054537 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.7474. Min Act: -0.1700
Data Index: 689318 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8099. Min Act: -0.1700
Data Index: 607084 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0911. Min Range: -5.0911
Max Act: 4.8099. Min Act: -0.1700
Data Index: 113678 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19