Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 93 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.5721. Min Act: -0.1700
Data Index: 314715 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.5721. Min Act: -0.1700
Data Index: 155282 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.5559. Min Act: -0.1700
Data Index: 616390 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.5236. Min Act: -0.1700
Data Index: 1385017 (Python Code)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4913. Min Act: -0.1700
Data Index: 1352440 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4913. Min Act: -0.1700
Data Index: 914319 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4588. Min Act: -0.1700
Data Index: 143641 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 1639465 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 1472381 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 780981 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4588. Min Act: -0.1700
Data Index: 292368 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4588. Min Act: -0.1700
Data Index: 791549 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 818988 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 60112 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 335435 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 387183 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4426. Min Act: -0.1700
Data Index: 522855 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4263. Min Act: -0.1700
Data Index: 455709 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4263. Min Act: -0.1700
Data Index: 132789 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5721. Min Range: -2.5721
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1312122 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19