Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1334 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6760. Min Act: -0.1700
Data Index: 1589295 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 1299334 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6599. Min Act: -0.1700
Data Index: 816465 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6439. Min Act: -0.1700
Data Index: 284921 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6599. Min Act: -0.1700
Data Index: 240565 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6118. Min Act: -0.1700
Data Index: 1020923 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 341611 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 304834 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 781520 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 1392045 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6118. Min Act: -0.1700
Data Index: 1385707 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6278. Min Act: -0.1700
Data Index: 907409 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5957. Min Act: -0.1700
Data Index: 211293 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6118. Min Act: -0.1700
Data Index: 384643 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5957. Min Act: -0.1700
Data Index: 1019530 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5635. Min Act: -0.1700
Data Index: 674244 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5957. Min Act: -0.1700
Data Index: 557370 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.6118. Min Act: -0.1700
Data Index: 1650508 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5796. Min Act: -0.1700
Data Index: 1585456 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6760. Min Range: -2.6760
Max Act: 2.5796. Min Act: -0.1700
Data Index: 1484090 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19