Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2039 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.8568. Min Act: -0.1700
Data Index: 759787 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.7006. Min Act: -0.1700
Data Index: 603057 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.7631. Min Act: -0.1700
Data Index: 1157236 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.7318. Min Act: -0.1700
Data Index: 13756 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 390646 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.7006. Min Act: -0.1700
Data Index: 567305 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 32833 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 610844 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6068. Min Act: -0.1700
Data Index: 650789 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 736768 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6693. Min Act: -0.1700
Data Index: 814857 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.5756. Min Act: -0.1700
Data Index: 186949 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 1128895 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6693. Min Act: -0.1700
Data Index: 1173651 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6068. Min Act: -0.1700
Data Index: 119396 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.5756. Min Act: -0.1700
Data Index: 601292 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.5443. Min Act: -0.1700
Data Index: 144564 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.5443. Min Act: -0.1700
Data Index: 797332 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1699
Data Index: 816699 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8568. Min Range: -4.8568
Max Act: 4.6381. Min Act: -0.1700
Data Index: 1128103 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19