Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 752 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1877. Min Range: -5.1877
Max Act: 5.1877. Min Act: -0.1700
Data Index: 253534 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.9377. Min Act: -0.1700
Data Index: 1191032 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1038459 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.9377. Min Act: -0.1700
Data Index: 1403090 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.9065. Min Act: -0.1700
Data Index: 53066 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8752. Min Act: -0.1700
Data Index: 156294 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.9065. Min Act: -0.1700
Data Index: 240002 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8440. Min Act: -0.1700
Data Index: 614464 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8440. Min Act: -0.1700
Data Index: 761528 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1095622 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1527263 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8440. Min Act: -0.1700
Data Index: 666422 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.7815. Min Act: -0.1700
Data Index: 11706 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8440. Min Act: -0.1700
Data Index: 802729 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8127. Min Act: -0.1700
Data Index: 1098710 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8127. Min Act: -0.1700
Data Index: 539547 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.7815. Min Act: -0.1700
Data Index: 1482526 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8127. Min Act: -0.1700
Data Index: 1387197 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8127. Min Act: -0.1700
Data Index: 927580 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1877. Min Range: -5.1877
Max Act: 4.8127. Min Act: -0.1700
Data Index: 365659 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19