Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 733 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.6115. Min Act: -0.1699
Data Index: 619725 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.5490. Min Act: -0.1700
Data Index: 585432 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.5490. Min Act: -0.1699
Data Index: 836478 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.4865. Min Act: -0.1700
Data Index: 234017 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.3615. Min Act: -0.1694
Data Index: 922670 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.3615. Min Act: -0.1699
Data Index: 521674 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.3615. Min Act: -0.1700
Data Index: 492170 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1740. Min Act: -0.1700
Data Index: 587550 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.2365. Min Act: -0.1700
Data Index: 1043152 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1740. Min Act: -0.1700
Data Index: 1306522 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1115. Min Act: -0.1700
Data Index: 34086 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1115. Min Act: -0.1700
Data Index: 845944 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1740. Min Act: -0.1700
Data Index: 1335620 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.2365. Min Act: -0.1700
Data Index: 1055134 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.0802. Min Act: -0.1699
Data Index: 913461 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1740. Min Act: -0.1700
Data Index: 231097 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.0490. Min Act: -0.1700
Data Index: 880158 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1740. Min Act: -0.1700
Data Index: 251034 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1115. Min Act: -0.1700
Data Index: 553470 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6115. Min Range: -6.6115
Max Act: 6.1115. Min Act: -0.1700
Data Index: 1353560 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19