Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 25 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 7.1511. Min Range: -7.1511
Max Act: 7.1511. Min Act: -0.1700
Data Index: 618825 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.9245. Min Act: -0.1700
Data Index: 751239 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.9558. Min Act: -0.1700
Data Index: 1488962 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.8542. Min Act: -0.1700
Data Index: 1628793 (Python Code)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.9011. Min Act: -0.1700
Data Index: 408978 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.7839. Min Act: -0.1700
Data Index: 353208 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.7214. Min Act: -0.1700
Data Index: 1554863 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6823. Min Act: -0.1700
Data Index: 1436717 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.7214. Min Act: -0.1700
Data Index: 1415631 (Python Code)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6980. Min Act: -0.1700
Data Index: 1419194 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6277. Min Act: -0.1700
Data Index: 1464068 (Python Code)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6745. Min Act: -0.1700
Data Index: 1647094 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6823. Min Act: -0.1700
Data Index: 237099 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6277. Min Act: -0.1700
Data Index: 1489691 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.6120. Min Act: -0.1700
Data Index: 1547800 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.5495. Min Act: -0.1700
Data Index: 1055922 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.5730. Min Act: -0.1700
Data Index: 1494468 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.5105. Min Act: -0.1700
Data Index: 652914 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.5417. Min Act: -0.1700
Data Index: 1420589 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1511. Min Range: -7.1511
Max Act: 6.5652. Min Act: -0.1700
Data Index: 1287125 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19