Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1837 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.6880. Min Act: -0.1700
Data Index: 1101081 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1055338 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1481093 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5756. Min Act: -0.1700
Data Index: 774368 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5756. Min Act: -0.1700
Data Index: 61406 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5756. Min Act: -0.1700
Data Index: 638735 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5594. Min Act: -0.1700
Data Index: 461421 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5594. Min Act: -0.1700
Data Index: 595473 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5433. Min Act: -0.1700
Data Index: 929866 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5433. Min Act: -0.1700
Data Index: 459564 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5271. Min Act: -0.1700
Data Index: 349746 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5433. Min Act: -0.1700
Data Index: 1025294 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5433. Min Act: -0.1700
Data Index: 176363 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5110. Min Act: -0.1700
Data Index: 311988 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5110. Min Act: -0.1700
Data Index: 510832 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5271. Min Act: -0.1700
Data Index: 823906 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5271. Min Act: -0.1700
Data Index: 1093672 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5271. Min Act: -0.1700
Data Index: 805805 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5271. Min Act: -0.1700
Data Index: 1029001 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6880. Min Range: -2.6880
Max Act: 2.5110. Min Act: -0.1700
Data Index: 1154170 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19